> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Upstash MCP server

The Upstash MCP connector routes your AI agent's tool calls to Upstash's own MCP server through Scalekit. Each user signs in to Upstash once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 77 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Databases, Developer Tools
**Tools:** 77: 28 read, 9 write, 40 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Upstash MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=UPSTASHMCP)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Upstash MCP connection

   In **AgentKit > Connections**, create an Upstash MCP connection and copy its redirect URI. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Register an OAuth app

   Upstash MCP server connections use your own OAuth app. Register one with Upstash MCP server and add the redirect URI you copied.

   Then enter the app's Client ID and Client Secret on the Upstash MCP connection.

5. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'upstashmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Upstash MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'upstashmcp_qstash_list_users',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "upstashmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Upstash MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="upstashmcp_qstash_list_users",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'upstashmcp_blob_download_url',
  toolInput: {
    bucket_id: '<bucket_id>',
    files: [],
  },
  connector: 'upstashmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="upstashmcp_blob_download_url",
    tool_input={
        "bucket_id": "<bucket_id>",
        "files": [],
    },
    connection_name="upstashmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `upstashmcp_blob_download_url`

Get Blob Download URL · Read-only

Mints short-lived presigned GET URLs for objects in a Blob bucket, so their bytes are downloaded straight from storage — a `curl` inside a box, a browser — without passing through this server. This is the way to read a **private** bucket, whose objects have no public link; on a public bucket the permanent `public_url` works too and is returned alongside. The URLs only read, so they are available on read-only connections. A URL lives at most 10 minutes; set `download_as` to have storage serve the object as an attachment with that filename. A missing object is a 404 from storage when the URL is fetched, not an error here.

Read only: yes. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket_id` (`string`, required): The bucket's id, from blob_bucket list or create
- `files` (`array`, required): The objects to mint download URLs for, one entry each
- `expires_in` (`integer`, optional): How long the URLs live, in seconds (default and maximum 600, the lifetime of the credential that signs them)

Example input: `{"bucket_id":"<bucket_id>","files":[]}`

### `upstashmcp_box_account`

Get Box Account · Read-only

Account-wide views across every box. Actions: summary (each active box with its cost; status deleted lists the deleted ones instead), billing (this month's token and compute totals), logs (log lines from all boxes; limit, offset, level, source, search, start_time and end_time filter them).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `summary`, `billing`, `logs`.
- `end_time` (`integer`, optional): Unix seconds
- `level` (`string`, optional): No description. One of: `info`, `warn`, `error`.
- `limit` (`integer`, optional): No description.
- `offset` (`integer`, optional): No description.
- `search` (`string`, optional): No description.
- `source` (`string`, optional): No description.
- `start_time` (`integer`, optional): Unix seconds
- `status` (`string`, optional): Which boxes to summarise (summary, default: active). One of: `active`, `deleted`.

Example input: `{"action":"summary"}`

### `upstashmcp_box_logs`

Get Box Logs · Read-only

Reads a box's timestamped log entries — system, user and agent sources — which is how to find out what happened inside it. Filterable by source, level, free-text search and a timestamp window.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `box_id` (`string`, required): The box ID (its name works too)
- `end_time` (`integer`, optional): Only entries at or before this Unix timestamp (seconds)
- `level` (`string`, optional): Only entries at this level. One of: `info`, `warn`, `error`.
- `limit` (`integer`, optional): Maximum entries to return (max 1000, default 100)
- `offset` (`integer`, optional): Entries to skip, for paging (default 0)
- `search` (`string`, optional): Only entries whose message matches this text
- `source` (`string`, optional): Only entries from this source. One of: `system`, `user`, `agent`.
- `start_time` (`integer`, optional): Only entries at or after this Unix timestamp (seconds)

Example input: `{"box_id":"<box_id>"}`

### `upstashmcp_box_metrics`

Get Box Metrics · Read-only

Resource and token usage for a box. Actions: current (CPU, memory and disk right now), history (a time series; range such as 1h or 24h, step such as 1m), tokens (token counts and cost over the last days), steps (the agent's commits, one per prompt, newest first), step_diff (needs sha; the diff one step made).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `current`, `history`, `tokens`, `steps`, `step_diff`.
- `box_id` (`string`, required): The box ID (its name works too)
- `days` (`integer`, optional): Days of token usage to cover
- `range` (`string`, optional): Time span for history, e.g. 1h, 24h, 7d
- `sha` (`string`, optional): Step commit (step_diff)
- `step` (`string`, optional): Resolution for history, e.g. 1m, 5m, 1h

Example input: `{"action":"current","box_id":"<box_id>"}`

### `upstashmcp_console_redis_keys`

List Redis Keys (Console) · Read-only

Console only: one SCAN page of a Redis database with each key's type and TTL.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `count` (`integer`, optional): No description. Default: `100`.
- `cursor` (`string`, optional): No description. Default: `0`.
- `match` (`string`, optional): No description.
- `type` (`string`, optional): Only keys of this type (SCAN's TYPE option). One of: `string`, `hash`, `list`, `set`, `zset`, `stream`, `json`.

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_console_redis_value`

Read Redis Value (Console) · Read-only

Console only: one Redis key's type, TTL, size and a bounded read of its value.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `key` (`string`, required): No description.

Example input: `{"databaseId":"<databaseId>","key":"<key>"}`

### `upstashmcp_dlq_list`

List Dead Letter Queue · Read-only

Lists the dead-letter queue for QStash messages or Workflow runs (service picks which). Paginated via cursor.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `service` (`string`, required): Which service the operation targets: plain QStash messaging or Upstash Workflow. One of: `qstash`, `workflow`.
- `cursor` (`string`, optional): No description.

Example input: `{"region":"eu","service":"qstash"}`

### `upstashmcp_index_fetch`

Fetch Index Documents · Read-only

Fetches documents by ID. Payload e.g. {"ids":["a","b"],"includeMetadata":true}, or {"prefix":"doc-","includeMetadata":true} to match an ID prefix.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON fetch payload
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `namespace` (`string`, optional): Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces

Example input: `{"indexId":"<indexId>","payload":"<payload>","service":"vector"}`

### `upstashmcp_index_get`

Get Index · Read-only

Gets details of one Vector index or Search database (endpoint, models, limits, usage). Its REST tokens are included only when include_credentials is true and the connection is read-write; on a read-only connection they are omitted (get them from the Upstash console).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_get_stats`

Get Index Usage Stats · Read-only

Gets usage statistics of one Vector index or Search database: queries and updates today and this month, storage, bandwidth and cost this month, queries and updates per day, throughput and latency (mean and p99) over the period, and document count and data size over time. Search databases add rerank and input-enrichment figures.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `period` (`string`, optional): Window the time series cover; the API's default when omitted. Daily and monthly totals ignore it. One of: `1h`, `3h`, `12h`, `1d`, `3d`, `7d`.

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_info`

Get Index Info · Read-only

Gets runtime info: total and pending document counts, index size, and a per-namespace breakdown. For Search those namespaces are its named indexes, with their document counts.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_list`

List Indexes · Read-only

Lists the Upstash Vector indexes or Search databases in the authorized account scope. Never includes tokens — call index_get with include_credentials for one of them.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"service":"vector"}`

### `upstashmcp_index_list_namespaces`

List Index Namespaces · Read-only

Lists the namespaces of a Vector index — or, for a Search database, its named indexes, which are the same thing. This is what search.listIndexes() calls.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_range`

Range Over Index Documents · Read-only

Iterates through the documents of a namespace, a page at a time. Payload e.g. {"cursor":"0","limit":100,"includeMetadata":true}; reuse the returned cursor for the next page, and stop to ask the user if the results get large.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON range payload
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `namespace` (`string`, optional): Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces

Example input: `{"indexId":"<indexId>","payload":"<payload>","service":"vector"}`

### `upstashmcp_logs_list`

List Logs · Read-only

Lists delivery/run logs for QStash messages or Workflow runs (service picks which), newest first. Paginated via cursor. This is the way to inspect a Workflow run by ID, whether it has finished or is still running: pass service workflow and workflowRunId, and the entry holds the run's state, its steps and their error bodies, in one call. workflowRunId, workflowUrl, state, workflowCreatedAt and label filter Workflow runs and are refused for service qstash; count works for both. QStash and Workflow only: Upstash keeps no command or request log for Redis databases (only the Enterprise audit-log add-on records commands, and it is not exposed here), and SLOWLOG and ACL LOG are not available on them. For Redis activity use redis_get_stats, and redis_get_insights or redis_get_traffic when the database has Prod Pack or a Pro plan.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `service` (`string`, required): Which service the operation targets: plain QStash messaging or Upstash Workflow. One of: `qstash`, `workflow`.
- `count` (`integer`, optional): Maximum number of entries (Workflow: runs) to return
- `cursor` (`string`, optional): Pagination cursor from a previous call
- `label` (`string`, optional): Workflow only: runs triggered with this label
- `state` (`string`, optional): Workflow only: runs that reached this state. Every run has reached RUN_STARTED, so it matches all runs; runs still in progress are the ones whose workflowState is RUN_STARTED in the result. One of: `RUN_STARTED`, `RUN_SUCCESS`, `RUN_FAILED`, `RUN_CANCELED`.
- `workflowCreatedAt` (`integer`, optional): Workflow only: the run's creation time in Unix milliseconds, as its workflowRunCreatedAt field shows
- `workflowRunId` (`string`, optional): Workflow only: return just this run. IDs start with wfr_ (a custom ID my-run-1 is stored as wfr_my-run-1). Several runs can share an ID; workflowCreatedAt picks one.
- `workflowUrl` (`string`, optional): Workflow only: runs of this workflow endpoint URL (exact match)

Example input: `{"region":"eu","service":"qstash"}`

### `upstashmcp_qstash_flow_control_get`

Get QStash Flow Control · Read-only

Gets flow-control state: rate/parallelism info for a flow-control key, or the account's global parallelism when key is omitted.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `key` (`string`, optional): Flow-control key (omit for global parallelism)

Example input: `{"region":"eu"}`

### `upstashmcp_qstash_get_stats`

Get QStash Usage Stats · Read-only

Gets usage statistics of a region's QStash user, which QStash and Workflow share. daily_requests has one point per day of the current month (y: QStash messages, workflow_message: the Workflow share of them, workflow_run: Workflow runs), as do daily_billings (cost) and daily_bandwidths; days still to come in the month are zeros. daily_qstash_messages (delivered, failed, retry, error, canceled, total) and daily_workflow_messages (success, failed, canceled, total) are today's running counts by outcome, sampled across `period` and reset at 00:00 UTC, so their last point is today so far. Also global parallelism over the period and the DLQ size. `service` keeps only one side's outcome series. With refresh, the API recomputes the cached figures first.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `period` (`string`, optional): Window the time series cover; the API's default when omitted. Daily and monthly totals ignore it. One of: `1h`, `3h`, `12h`, `1d`, `3d`, `7d`.
- `refresh` (`boolean`, optional): Ask the API to recompute the cached figures before reading them, as the Upstash console does when it opens the page. Needs a read-write connection; when the refresh is refused the cached figures are still returned, with refreshed: false
- `service` (`string`, optional): Keep only QStash's or only Workflow's message series (default: both). One of: `qstash`, `workflow`.

Example input: `{"region":"eu"}`

### `upstashmcp_qstash_list_schedules`

List QStash Schedules · Read-only

Lists QStash schedules in a region.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.

Example input: `{"region":"eu"}`

### `upstashmcp_qstash_list_users`

List QStash Users · Read-only

Lists the QStash users in the authorized account scope, one per region. Each region's REST tokens, and with `region` ("eu" or "us") that region's request signing keys ({ current, next }, fetched live), are included only when include_credentials is true and the connection is read-write; on a read-only connection they are omitted. The REST base URL for a region is https://qstash-<region>.upstash.io (e.g. qstash-us-east-1.upstash.io).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless
- `region` (`string`, optional): Return only this region's user (with its request signing keys when include_credentials is true). One of: `eu`, `us`.

Example input: `{}`

### `upstashmcp_redis_get_database`

Get Redis Database · Read-only

Gets details of a single Upstash Redis database: endpoint, region, plan, limits and state. Credentials (password and REST tokens) are included only when include_credentials is true and the connection is read-write; on a read-only connection they are omitted (get them from the Upstash console). A database with Protect Credentials enabled (is_password_protected) has none to return. A branch has root_database_id (the database it belongs to) and source_database_id (the database or branch it was copied from, which may since have been deleted), and can only be looked up by its ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_get_insights`

Get Redis Insights · Read-only

Gets the Redis Insights series of a database, as the Upstash console's Insights tab shows them: latency percentiles (overall, read, write, command, Lua, replication, wait), throughput, bandwidth, disk, expired entries and replication lag, for the whole database and per region (or one replica). Also counters over the period (throttled commands, auth failures, over-size requests, undeliverable messages, Lua executions, failures, timeouts and memory-limit hits, REST commands, connections opened), each metric's mean now against the window before, and anomalies the backend detected (start, peak, baseline and change, heaviest first). Start with anomalies and counters when asked why a database is slow or failing. `metrics` trims the per-metric series, which are most of the response. Needs Prod Pack (or a Pro or Enterprise plan): without it the API answers 404 "insights require Prod Pack"; redis_set_prod_pack turns it on.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `metrics` (`array`, optional): Return only these metrics' series, comparisons and anomalies (default: all)
- `period` (`string`, optional): Window the series and counters cover (default 1d). One of: `1h`, `3h`, `12h`, `1d`, `3d`, `7d`, `30d`.
- `replica` (`string`, optional): Narrow the series to one replica (a group key from `groups`); default: the whole database, per region

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_get_stats`

Get Redis Usage Stats · Read-only

Gets usage statistics of an Upstash Redis database: throughput, latency, hits and misses, keys, data size and connections over the period, requests per day, and this month's requests, bandwidth and cost. With refresh, the API recomputes the cached figures first. Commands reach these figures about two minutes after they run, and refresh does not shorten that; it only brings dailyrequests and the monthly totals up to what has been collected. So for a database created or used in the last few minutes, a count of 0 means not counted yet, not no traffic: tell the user the numbers trail by a couple of minutes and offer to check again, rather than reporting 0.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `period` (`string`, optional): Window the time series cover; the API's default when omitted. Daily and monthly totals ignore it. One of: `1h`, `3h`, `12h`, `1d`, `3d`, `7d`.
- `refresh` (`boolean`, optional): Ask the API to recompute the cached figures before reading them, as the Upstash console does when it opens the page. Needs a read-write connection; when the refresh is refused the cached figures are still returned, with refreshed: false

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_get_traffic`

Get Redis Traffic · Read-only

Gets where a Redis database's traffic comes from and how it is served: the client networks the proxies sampled (masked prefixes, cloud provider and region, share), the SDKs, platforms and runtimes clients report with their retry rate, routes from entry region to serving region with requests, connections, bytes, errors and whether they cross regions, the entry regions by share, the cross-region share of bytes, and REST vs. Lua command counts. Use it to find clients far from the database, or traffic served cross-region. Needs Prod Pack (or a Pro or Enterprise plan): without it the API answers 404 "insights require Prod Pack"; redis_set_prod_pack turns it on.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `period` (`string`, optional): Window the series and counters cover (default 1d). One of: `1h`, `3h`, `12h`, `1d`, `3d`, `7d`, `30d`.

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_list_backups`

List Redis Backups · Read-only

Lists backups of an Upstash Redis database.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_list_databases`

List Redis Databases · Read-only

Lists all Upstash Redis databases in the authorized account scope. Never includes credentials — call redis_get_database with include_credentials for one database's. Branches are listed too: root_database_id is set on a branch and names the database it belongs to, so filter on it to find a database's branches.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `upstashmcp_search_query`

Search Documents · Read-only

Runs a full-text and semantic search over one named index of a Search database. No tokens needed. Payload per the Search REST API, e.g. {"query":"space odyssey","limit":5,"reranking":true}.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `indexName` (`string`, required): The named index inside the Search database
- `payload` (`string`, required): JSON search payload

Example input: `{"indexId":"<indexId>","indexName":"<indexName>","payload":"<payload>"}`

### `upstashmcp_upstash_console`

Open Upstash Console · Read-only

Opens the Upstash console: an interactive view of the user's Redis databases and keys, QStash and Workflow schedules, logs and DLQs, Vector and Search indexes, Boxes and Blob buckets. Call it when the user asks to see, browse or open their Upstash resources rather than for a specific answer. To show one resource, pass product and resource (and a tab): the console opens on it, and the user can still navigate from there.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `product` (`string`, optional): Open on this product's page instead of the first one. One of: `redis`, `qstash`, `workflow`, `vector`, `search`, `box`, `blob`.
- `resource` (`string`, optional): Select this resource, by ID or name: a Redis database, Vector index, Search database, box or Blob bucket. For QStash and Workflow, the region: eu or us
- `tab` (`string`, optional): Open this tab: overview and stats (every product); settings (every product: a Danger zone with deleting the resource and, except Box, resetting its credentials; Redis, QStash, Workflow, Vector, Search also plan, Prod Pack and budget, and Redis read regions, eviction and auto-upgrade); data, cli, insights (Redis); data (Vector, Search); publish, schedules, logs, dlq (QStash); trigger, runs, dlq (Workflow); logs, snapshots (Box); objects (Blob). One of: `overview`, `data`, `cli`, `stats`, `insights`, `publish`, `trigger`, `schedules`, `logs`, `runs`, `dlq`, `objects`, `snapshots`, `settings`.

Example input: `{}`

### `upstashmcp_vector_query`

Query Vectors · Read-only

Queries a Vector index by vector similarity. No tokens needed. Payload per the Vector REST API, e.g. {"vector":[...],"topK":10,"includeMetadata":true} — or with useData=true, {"data":"text to embed","topK":10} for embedding-model indexes. For a Search database use search_query instead.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON payload as the Vector REST API expects
- `namespace` (`string`, optional): Namespace to query (omit for the default namespace)
- `useData` (`boolean`, optional): true = /query-data (server-side embedding)

Example input: `{"indexId":"<indexId>","payload":"<payload>"}`

### `upstashmcp_blob_upload_url`

Get Blob Upload URL · Write

Mints presigned PUT URLs for paths in a Blob bucket, so files are uploaded straight to storage from wherever they already are — a `curl` inside a box, a CI job — without their bytes passing through this server. Send the returned `headers` verbatim with the PUT: they are part of the signature, so a changed, dropped or added header is a 403 from storage. A URL lives at most 10 minutes, so mint it immediately before uploading rather than up front. On a public bucket each file also comes back with `public_url`, the permanent link to use once the upload succeeds (in a PR body, say); a private bucket has none. The result's `curl_example` is the first file's real command line.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket_id` (`string`, required): The bucket's id, from blob_bucket list or create
- `files` (`array`, required): The files to mint upload URLs for, one entry each
- `expires_in` (`integer`, optional): How long the URLs live, in seconds (default and maximum 600, the lifetime of the credential that signs them)

Example input: `{"bucket_id":"<bucket_id>","files":[]}`

### `upstashmcp_box_browser`

Control Box Browser · Write

Drives the headless Chromium in a box created with browser=true. Actions: goto (navigate to url and return the page), content (read the current page as title/url/text/links), screenshot (PNG of the page — returned as an image unless path is given, in which case it is saved into the box at that path instead), tabs (list the open tabs), tab_new (open a tab, optionally at url), tab_close (needs tab), live_view (a view-only page a person can open to watch the tab live — frames flow out, no input goes in, so hand the URL to the user rather than trying to click in it). box_id is required for every action.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `goto`, `content`, `screenshot`, `tabs`, `tab_new`, `tab_close`, `live_view`.
- `box_id` (`string`, required): The box ID (its name works too)
- `full_page` (`boolean`, optional): Capture the whole scrollable page rather than the viewport (screenshot)
- `path` (`string`, optional): Save the screenshot at this path inside the box instead of returning the image (screenshot)
- `tab` (`string`, optional): CDP target id of the tab, from the tabs action (required for tab_close; elsewhere the active tab is used when omitted)
- `url` (`string`, optional): URL to open (required for goto, optional for tab_new)

Example input: `{"action":"goto","box_id":"<box_id>"}`

### `upstashmcp_index_create`

Create Index · Write

Creates a Vector index or a Search database and returns it. Its REST tokens are included only when include_credentials is true — set it when the user is going to configure an app with it; they can also be fetched later with index_get. Search takes only name, region and plan — its embedding, reranking and enrichment models are fixed by the service, and its named indexes are created implicitly by the first search_upsert. Vector takes the rest: dimensions come from the embedding model when one is given, so pass dimensionCount only for an index you will supply your own vectors to; a SPARSE index takes neither and is described by sparseEmbeddingModel alone; a HYBRID index takes both models or neither. Plans and prices (Search is billed as Vector): https://upstash.com/pricing/vector.md; when the user picks fixed, confirm its monthly price with them first.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Index or database name
- `region` (`string`, required): Region to create in. Vector: an AWS or GCP region such as us-east-1 or eu-west-1 (the API rejects one it has no pool for). Search: only us-central1 or eu-west-1
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `dimensionCount` (`integer`, optional): Vector only. Required for a DENSE index with no embedding model; derived from the model otherwise, and rejected for SPARSE
- `embeddingModel` (`string`, optional): Vector only. Upstash-hosted dense embedding model, so you can upsert text instead of vectors. Sets dimensionCount. One of: `BGE_SMALL_EN_V1_5`, `BGE_BASE_EN_V1_5`, `BGE_LARGE_EN_V1_5`, `BGE_M3`, `TEXT_EMBEDDING_3_SMALL`.
- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless
- `indexType` (`string`, optional): Vector only. Index type (default DENSE). One of: `DENSE`, `SPARSE`, `HYBRID`.
- `plan` (`string`, optional): Plan (default: free for accounts without a payment method, payg otherwise). One of: `free`, `payg`, `fixed`, `pro`.
- `similarityFunction` (`string`, optional): Vector only. Similarity function (default EUCLIDEAN). Not applicable to SPARSE. One of: `COSINE`, `EUCLIDEAN`, `DOT_PRODUCT`.
- `sparseEmbeddingModel` (`string`, optional): Vector only. Sparse embedding model, for SPARSE and HYBRID indexes. One of: `BGE_M3`, `BM25`.

Example input: `{"name":"<name>","region":"<region>","service":"vector"}`

### `upstashmcp_qstash_publish_message`

Publish QStash Message · Write

Publishes a message to a destination URL via QStash. No tokens needed — the region's QStash token is resolved server-side.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `destinationUrl` (`string`, required): The URL QStash should deliver the message to
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `body` (`string`, optional): Message body
- `contentType` (`string`, optional): Content-Type of the body (default application/json)
- `delaySeconds` (`integer`, optional): Delivery delay in seconds
- `retries` (`integer`, optional): Max retries on delivery failure

Example input: `{"destinationUrl":"<destinationUrl>","region":"eu"}`

### `upstashmcp_redis_create_backup`

Create Redis Backup · Write

Creates a manual backup of an Upstash Redis database.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `name` (`string`, required): Name for the backup

Example input: `{"databaseId":"<databaseId>","name":"<name>"}`

### `upstashmcp_redis_create_branch`

Create Redis Branch · Write

Creates a branch of an Upstash Redis database: a point-in-time copy of its data with its own endpoint and password, for testing against real data. Later changes on either side stay separate, and a branch cannot be merged back. It returns right away with state "creating": poll redis_get_database with the returned database_id until state is "active" before using it, which usually takes seconds. If that lookup starts returning 404, creation failed and the branch was removed. A branch has a single replica and no read regions, and is billed as pay-as-you-go for its requests, storage and bandwidth whatever the source's plan (https://upstash.com/pricing/redis.md), so tell the user before copying a large database. Needs an account with a payment method and a global source database on a pay-as-you-go, fixed or enterprise plan; free, legacy Pro, IP-allowlisted, HIPAA, ephemeral, suspended and busy databases are refused. A branch can itself be branched. Use redis_delete_database to delete a branch and redis_rename_database to rename one.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `databaseId` (`string`, required): The ID of the database or branch to copy
- `name` (`string`, required): Branch name, up to 100 characters: letters, numbers, hyphens, underscores and dots, starting and ending with a letter or number. Unique among the branches of one database
- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless

Example input: `{"databaseId":"<databaseId>","name":"<name>"}`

### `upstashmcp_redis_create_database`

Create Redis Database · Write

Creates a new Upstash Redis database and returns it. Its credentials (password and REST tokens) are included only when include_credentials is true — set it when the user is going to configure an app with the new database; they can also be fetched later with redis_get_database. Without plan the database is free or pay-as-you-go, depending on whether the account has a payment method. Plans and prices: https://upstash.com/pricing/redis.md; when the user picks a fixed tier, confirm its monthly price with them first.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Database name (alphanumeric)
- `primaryRegion` (`string`, required): Primary region, e.g. us-east-1, eu-west-1
- `include_credentials` (`boolean`, optional): Set true only when the user asks for connection details or wants to configure an app with this resource: the result then includes its credentials (REST tokens, password). Default false — metadata only. On a read-only connection credentials are omitted regardless
- `plan` (`string`, optional): Plan to create the database on. On the pricing page "Pay as You Go" is payg and "Fixed 250MB" … "Fixed 500GB" are fixed_250mb … fixed_500gb. One of: `free`, `payg`, `fixed_250mb`, `fixed_1gb`, `fixed_5gb`, `fixed_10gb`, `fixed_50gb`, `fixed_100gb`, `fixed_500gb`.
- `readRegions` (`array`, optional): Optional read-replica regions

Example input: `{"name":"<name>","primaryRegion":"<primaryRegion>"}`

### `upstashmcp_redis_set_daily_backup`

Set Redis Daily Backup · Write

Turns automatic daily backups of an Upstash Redis database on or off. The first backup runs about 24 hours after turning them on; redis_list_backups lists them and redis_get_database shows daily_backup_enabled and next_daily_backup_time. Free databases cannot use backups, nor can suspended ones, databases managed through Fly, Heroku or DigitalOcean, or databases where support has disabled backups; the Finance team role cannot change it. Prod Pack includes daily backups, so they cannot be turned off while Prod Pack is on; HIPAA databases cannot turn them off either. Nothing is sent when backups are already in the requested state.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `enabled` (`boolean`, required): true to turn daily backups on, false to turn them off

Example input: `{"databaseId":"<databaseId>","enabled":true}`

### `upstashmcp_submit_feedback_to_upstash_team`

Send Feedback to the Upstash Team · Write

Report friction with this MCP server to the Upstash team that builds it.

Use it when:
- no tool could do what the user asked
- a tool failed, returned wrong data, or was confusing
- you have an idea that would make the tools better

Call it at most once per task, after you finish or give up. The feedback goes to the Upstash team, not to the user's account. Do not include secrets, credentials, database contents or personal data.

Example: task 'find the slowest Redis commands', kind 'missing', impact 'worked_around', description 'redis_get_insights has latency percentiles but no per-command breakdown; I ran SLOWLOG GET with redis_run_command.'

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `description` (`string`, required): What you tried, with the tool calls and any error, and what went wrong.
- `impact` (`string`, required): blocked: you could not finish; worked_around: you finished another way; friction: you finished, but it was harder than it should be. One of: `blocked`, `worked_around`, `friction`.
- `kind` (`string`, required): missing: no tool could do it; broken: a tool failed or returned something wrong; confusing: a tool or its description was unclear; idea: a suggestion. One of: `missing`, `broken`, `confusing`, `idea`.
- `task` (`string`, required): A short phrase naming what the user asked you to do.
- `tool_name` (`string`, optional): The tool of this server the feedback is about, if any.

Example input: `{"description":"<description>","impact":"blocked","kind":"missing","task":"<task>"}`

### `upstashmcp_blob_bucket`

Manage Blob Buckets · Destructive

Lists, gets, creates or deletes Upstash Blob buckets — object storage an agent can upload files to and link to afterwards. Blob has no plans to choose: storage, operations and bandwidth are free up to a monthly allowance and pay-as-you-go above it (https://upstash.com/pricing/blob.md). Actions: list (every bucket in the authorized account scope), get (needs bucket_id; with include_credentials the result also carries the bucket's `token`, the value `@upstash/blob` reads as UPSTASH_BLOB_TOKEN), stats (needs bucket_id; storage, bandwidth, operations and cost per day and per month, collected hourly, so today's row is partial), create (needs name), delete (needs bucket_id; permanent, and refused while the bucket still holds objects — empty it with blob_object delete first), reset_token (needs bucket_id; rotates the bucket token: the current token stops working at once, so apps need the new UPSTASH_BLOB_TOKEN from get with include_credentials; confirm with the user first). A public bucket serves its objects at a permanent URL under public_host, which is what you want for a link that has to keep working, such as an image embedded in a PR body; a private bucket has no public host and its objects are reachable only through short-lived signed URLs. The token is returned only by get with include_credentials on a read-write connection; on a read-only connection it is omitted regardless, and list, create, delete and reset_token never return it.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `list`, `get`, `stats`, `create`, `delete`, `reset_token`.
- `bucket_id` (`string`, optional): The bucket's id, from blob_bucket list (required for get, stats, delete and reset_token)
- `days` (`integer`, optional): stats only: daily rows to return, including today (max 90)
- `include_credentials` (`boolean`, optional): get only. Set true only when the user asks for the bucket's credentials or wants to configure an app with it (UPSTASH_BLOB_TOKEN): the result then includes `token`. Default false — metadata only. On a read-only connection the token is omitted regardless
- `months` (`integer`, optional): stats only: monthly rows to return, including this month (max 24)
- `name` (`string`, optional): Bucket name, unique within the account (required for create)
- `visibility` (`string`, optional): Whether the bucket's objects are served publicly (create, default: public). Public gives every object a permanent URL; private objects are reachable only through short-lived signed URLs. One of: `public`, `private`.

Example input: `{"action":"list"}`

### `upstashmcp_blob_object`

Manage Blob Objects · Destructive

Lists or deletes objects in an Upstash Blob bucket — their paths, sizes and links, never their bytes. Actions: list (needs bucket_id; optional prefix and cursor; up to 1000 objects per page, and a cursor in the result means more follow — pass it back to continue), delete (needs bucket_id and paths, up to 1000 exact keys; permanent, and a path that is already gone counts as deleted). To empty a bucket before blob_bucket delete, list a page, delete its paths, repeat until list comes back empty. Never returns bucket tokens.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `list`, `delete`.
- `bucket_id` (`string`, required): The bucket's id, from blob_bucket list or create
- `cursor` (`string`, optional): list only: where to continue from, as returned by the previous page
- `paths` (`array`, optional): delete only: the exact object keys to remove (up to 1000)
- `prefix` (`string`, optional): list only: objects whose key starts with this, e.g. 'proof/my-repo/'

Example input: `{"action":"list","bucket_id":"<bucket_id>"}`

### `upstashmcp_box_apikey`

Manage Box API Keys · Destructive

Manages Box API keys for the authorized account scope, the credential the Box SDK, CLI and deployed apps use. Actions: list (metadata only: id, name, prefix, never the secret), create (optional name; read_only: true makes a key that can read boxes, logs and files and run exec as a restricted user, gets 403 on every write, cannot wake a paused box and sees secrets masked, which suits monitoring or a debugging agent; returns the secret once, so surface it to the user to store), delete (needs api_key_id; anything still using the key stops working immediately). A key is account-scoped and independent of this connection: it keeps working after the OAuth grant that created it is revoked, so tell the user to delete it, here or in the Upstash console, once it is no longer needed. Read-only OAuth grants get 403 on create and delete.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `list`, `create`, `delete`.
- `api_key_id` (`string`, optional): Key id from list (required for delete)
- `name` (`string`, optional): Display name for the key (create)
- `read_only` (`boolean`, optional): Create a read-only key (create). Cannot be changed later

Example input: `{"action":"list"}`

### `upstashmcp_box_config`

Manage Box Config · Destructive

Changes a running box's configuration. Actions: get (model, MCP servers and enabled skills; labels are on box_manage get); set_model (needs model); add_label and remove_label (need label); add_skill and remove_skill (need skill, as owner/repo/skill-name); add_mcp_server (needs mcp_server) and remove_mcp_server (needs name); set_network_policy (needs network_policy); set_git_identity (needs git_user_name and git_user_email); get_init_command, set_init_command (needs init_command) and delete_init_command, which apply to keep-alive boxes only. Size, browser and keep_alive are fixed at create time. Read-only OAuth connections are refused with 403 on the actions that write.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `get`, `set_model`, `add_label`, `remove_label`, `add_skill`, `remove_skill`, `add_mcp_server`, `remove_mcp_server`, `set_network_policy`, `set_git_identity`, `get_init_command`, `set_init_command`, `delete_init_command`.
- `box_id` (`string`, required): The box ID (its name works too)
- `git_user_email` (`string`, optional): git user.email (set_git_identity)
- `git_user_name` (`string`, optional): git user.name (set_git_identity)
- `init_command` (`string`, optional): Startup script (set_init_command)
- `label` (`string`, optional): Label (add_label, remove_label)
- `mcp_server` (`object`, optional): Server to add (add_mcp_server)
- `model` (`string`, optional): Model identifier (set_model)
- `name` (`string`, optional): Server name (remove_mcp_server)
- `network_policy` (`object`, optional): Outbound policy; the lists apply to mode custom (set_network_policy)
- `skill` (`string`, optional): Skill id, owner/repo/skill-name (add_skill, remove_skill)

Example input: `{"action":"get","box_id":"<box_id>"}`

### `upstashmcp_box_env`

Manage Box Environment · Destructive

Account-level environment variables, merged into every box created afterwards; a box's own env_vars win for the same key, and a box that already exists is not changed. Actions: list (values come back masked), set (needs key and value), set_all (needs env_vars, and replaces the whole set), delete (needs key). Not a secrets store: a value set here is visible inside every future box. Read-only OAuth connections are refused with 403 on the actions that write.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `list`, `set`, `set_all`, `delete`.
- `env_vars` (`object`, optional): The full set (set_all)
- `key` (`string`, optional): Variable name (set, delete)
- `value` (`string`, optional): Variable value (set)

Example input: `{"action":"list"}`

### `upstashmcp_box_exec`

Run Command in Box · Destructive

Runs a shell command inside a box, waits for it to finish, and returns its exit code and output. Use it for file operations, package installs, builds, tests — anything a shell does. For repository work (clone, commit, push, pull request) use box_git, which also puts the GitHub credentials into the box. The command is an argv array, e.g. ['bash', '-c', 'ls -la']; an inline program is one too: ['node', '-e', code], ['python3', '-c', code] or ['npx', 'tsx', '-e', code], and content written with ['sh', '-c', 'printf %s "$1" > "$2"', 'sh', content, path] needs no quoting. `folder` defaults to /workspace/home, the workspace root; a clone sits at /workspace/home/<repo name>. To start something long-running (a dev server, say) without blocking, detach it inside the shell: ['sh', '-c', '( my-server > server.log 2>&1 & )']. A paused box is resumed first. Read-only OAuth connections cannot run commands: the box API refuses them with 403.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `box_id` (`string`, required): The box ID (its name works too)
- `command` (`array`, required): Command and arguments as an array, e.g. ['bash', '-c', 'ls -la']
- `folder` (`string`, optional): Working directory inside the box (defaults to /workspace/home)

Example input: `{"box_id":"<box_id>","command":[]}`

### `upstashmcp_box_git`

Run Git in Box · Destructive

Runs git inside a box. Authentication comes from the GitHub installation linked to the Upstash account — the tool takes no token, and a private repo works only if that installation can see it. Actions: clone (needs repo), status, diff, commit (needs message), checkout (needs branch), push, create_pr (needs title), create_issue (needs title). Anything else git does (add, log, rebase) is a box_exec command such as ['git', 'log', '-1']. Clone with this tool rather than with git in box_exec: clone is what puts the GitHub credentials into the box, and without them push and create_pr fail with a 500. A clone lands at /workspace/home/<repo name>; pass that as `folder` on every other action, since the default is the workspace root, which is not a repository. create_pr opens the pull request for the branch as it exists on the remote and pushes nothing itself, so push first, and give push the branch name: without one the API pushes to a branch named after the box. Read-only OAuth connections are refused with 403 on the actions that write (clone, commit, checkout, push, create_pr, create_issue).

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `clone`, `status`, `diff`, `commit`, `checkout`, `push`, `create_pr`, `create_issue`.
- `box_id` (`string`, required): The box ID (its name works too)
- `author_email` (`string`, optional): Override the commit author email (commit)
- `author_name` (`string`, optional): Override the commit author name (commit)
- `base` (`string`, optional): Branch the pull request merges into (create_pr, defaults to the repo's)
- `body` (`string`, optional): Description (create_pr, create_issue)
- `branch` (`string`, optional): Branch: to clone, to switch to (required for checkout), or to push
- `depth` (`integer`, optional): Clone depth; 0 or omitted clones the full history (clone)
- `folder` (`string`, optional): Working directory inside the box, normally the clone's folder such as /workspace/home/<repo name> (defaults to /workspace/home, which is not a repository). For clone: the directory name to clone into, relative to /workspace/home
- `message` (`string`, optional): Commit message (required for commit)
- `repo` (`string`, optional): Repository URL to clone, https/http/git/ssh (required for clone)
- `title` (`string`, optional): Title (required for create_pr and create_issue)

Example input: `{"action":"clone","box_id":"<box_id>"}`

### `upstashmcp_box_manage`

Manage Boxes · Destructive

Manages Upstash Boxes — sandboxed cloud containers with a shell, a filesystem and an optional headless browser. Actions: create (set browser=true to make box_browser usable), list (optionally filtered by label or status), get, status (cheaper than get, for polling), delete (permanent, takes the workspace with it; pass box_id for one box or box_ids for several in one call), pause, resume, fork (copies an idle or paused non-ephemeral box), reset (wipes the workspace back to a fresh box; the id survives). Every action except create and list needs box_id (delete accepts box_ids instead). There is no delete-everything: to clear an account, list first and pass the ids you mean. Ephemeral boxes need no paid plan and are cleaned up when their TTL expires; keep-alive boxes require one. size and keep_alive set what a box costs and cannot be changed after create; prices per size: https://upstash.com/pricing/box.md. Confirm with the user before creating a keep-alive box, which is billed for as long as it exists, used or not.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `create`, `list`, `get`, `status`, `delete`, `pause`, `resume`, `fork`, `reset`.
- `agent` (`string`, optional): Agent to install in the box (create, default: claude-code). One of: `claude-code`, `codex`, `opencode`, `cursor`.
- `attach_headers` (`object`, optional): Headers injected into outbound requests, keyed by host pattern, e.g. {'api.stripe.com': {'Authorization': 'Bearer ...'}} (create)
- `box_id` (`string`, optional): Box ID (required for get, status, pause, resume, fork, reset; delete takes this or box_ids)
- `box_ids` (`array`, optional): Several box IDs to delete in one call (delete only, at most 50); the result counts how many were deleted and how many failed
- `browser` (`boolean`, optional): Give the box a headless Chromium (create). Without it box_browser fails with 'browser is not enabled for this box'
- `clone_repo` (`string`, optional): Git repository URL to clone into the box on startup (create)
- `clone_token` (`string`, optional): Token for cloning a private repository (create)
- `env_vars` (`object`, optional): Environment variables to set inside the box (create)
- `ephemeral` (`boolean`, optional): Create a throwaway box that is deleted when its TTL expires (create)
- `git_user_email` (`string`, optional): git user.email inside the box (create)
- `git_user_name` (`string`, optional): git user.name inside the box (create)
- `init_command` (`string`, optional): Startup script run when the box starts; keep-alive boxes only (create)
- `keep_alive` (`boolean`, optional): Keep the box running rather than idling it (create, requires a paid plan; mutually exclusive with ephemeral)
- `label` (`string`, optional): Only return boxes carrying this label (list)
- `labels` (`array`, optional): Labels to tag the box with (create)
- `mcp_servers` (`array`, optional): MCP servers for the box's agent, an npm package or a remote url each (create)
- `model` (`string`, optional): LLM model the box's agent runs, e.g. 'claude/sonnet_4_6' or 'openai/o4-mini' (create). Agent runs use the provider key saved on the account in the Upstash Console; without one they fail, though the box still works for shell, files and git
- `name` (`string`, optional): Display name for the box (create)
- `network_policy` (`object`, optional): Outbound network policy; the lists apply to mode custom (create)
- `runtime` (`string`, optional): Runtime image, e.g. 'node' or 'python' (create, default: node)
- `size` (`string`, optional): Box size (create, default: small). One of: `small`, `medium`, `large`.
- `skills` (`array`, optional): Skills to install, each owner/repo/skill-name (create)
- `status` (`string`, optional): Which boxes to list (list, default: active). One of: `active`, `deleted`.
- `ttl` (`integer`, optional): Lifetime in seconds of an ephemeral box (create, max 259200 = 3 days)

Example input: `{"action":"create"}`

### `upstashmcp_box_preview`

Manage Box Preview URLs · Destructive

Manages public preview URLs for ports inside a box, so a service running in it is reachable from the internet. Actions: create (needs port; basic_auth or bearer_token add a generated credential, which is returned once and only here), list, delete (needs port). box_id is required for every action.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `create`, `list`, `delete`.
- `box_id` (`string`, required): The box ID (its name works too)
- `basic_auth` (`boolean`, optional): Protect the preview with a generated username and password (create)
- `bearer_token` (`boolean`, optional): Protect the preview with a generated bearer token (create)
- `port` (`integer`, optional): Port inside the box (required for create and delete)

Example input: `{"action":"create","box_id":"<box_id>"}`

### `upstashmcp_box_runs`

List Box Runs · Destructive

Inspects a box's run history — agent prompts, shell executions and browser runs — with their status, output, token usage and cost. Actions: list, get (needs run_id), cancel (needs run_id; only a run that is still running can be cancelled). box_id is required for every action.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): The action to perform. One of: `list`, `get`, `cancel`.
- `box_id` (`string`, required): The box ID (its name works too)
- `run_id` (`string`, optional): Run ID (required for get and cancel actions)

Example input: `{"action":"list","box_id":"<box_id>"}`

### `upstashmcp_box_schedules`

Manage Box Schedules · Destructive

Cron schedules that run a shell command or an agent prompt inside a box on a UTC cron expression. Actions: create (needs cron and either command or prompt), list, get, update, pause, resume, delete (the last five need schedule_id). update changes only the fields given, so a new cron leaves the command alone. An agent prompt runs on the provider key saved on the account (or set on the box) and fails without one. timeout is milliseconds; 0 clears it on update. Read-only OAuth connections are refused with 403 on the actions that write.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. One of: `create`, `list`, `get`, `update`, `pause`, `resume`, `delete`.
- `box_id` (`string`, required): The box ID (its name works too)
- `command` (`array`, optional): Command as an argv array, for a shell schedule
- `cron` (`string`, optional): Cron expression, UTC, e.g. '0 9 * * *'
- `folder` (`string`, optional): Working directory inside the box (defaults to /workspace/home)
- `model` (`string`, optional): Model for an agent schedule
- `prompt` (`string`, optional): Prompt, for an agent schedule
- `schedule_id` (`string`, optional): Schedule ID (required for get, update, pause, resume, delete)
- `timeout` (`integer`, optional): Milliseconds; 0 clears it on update

Example input: `{"action":"create","box_id":"<box_id>"}`

### `upstashmcp_box_snapshots`

Manage Box Snapshots · Destructive

Manages box snapshots — full filesystem copies a new box can be built from. Actions: create (needs box_id), list (one box's snapshots, needs box_id), list_all (every snapshot in the account), delete (needs box_id and snapshot_id), restore (needs snapshot_id; creates a NEW box from the snapshot and leaves the original alone, inheriting the snapshot's model and runtime unless they are overridden).

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): The action to perform. 'list' lists one box's snapshots, 'list_all' lists every snapshot in the account. One of: `create`, `list`, `list_all`, `delete`, `restore`.
- `box_id` (`string`, optional): Box ID (required for create, list, delete)
- `env_vars` (`object`, optional): Environment variables for the restored box (restore)
- `ephemeral` (`boolean`, optional): Create the restored box as ephemeral (restore)
- `labels` (`array`, optional): Labels for the restored box (restore)
- `model` (`string`, optional): LLM model for the restored box (restore, defaults to the snapshot's)
- `name` (`string`, optional): Name for the snapshot (create, auto-generated if omitted)
- `runtime` (`string`, optional): Override the snapshot's runtime for the restored box (restore)
- `snapshot_id` (`string`, optional): Snapshot ID (required for delete and restore)
- `ttl` (`integer`, optional): Lifetime in seconds of a restored ephemeral box (restore, max 3 days)

Example input: `{"action":"create"}`

### `upstashmcp_dlq_manage`

Manage Dead Letter Queue · Destructive

Manages a dead-letter-queue entry: get or delete (QStash and Workflow), restart or resume (Workflow only).

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): No description. One of: `get`, `delete`, `restart`, `resume`.
- `dlqId` (`string`, required): The DLQ entry ID
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `service` (`string`, required): Which service the operation targets: plain QStash messaging or Upstash Workflow. One of: `qstash`, `workflow`.

Example input: `{"action":"get","dlqId":"<dlqId>","region":"eu","service":"qstash"}`

### `upstashmcp_index_delete`

Delete Index · Destructive

PERMANENTLY deletes an entire Vector index or Search database, everything stored in it and its credentials. This cannot be undone. To empty one while keeping it, use index_reset; to remove a single namespace or named index, use index_delete_namespace.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_delete_documents`

Delete Index Documents · Destructive

Deletes documents from a namespace, leaving the namespace and the index in place. Payload e.g. {"ids":["a","b"]}, {"prefix":"doc-"} or {"filter":"..."}. To empty a namespace entirely use index_reset; to delete the index itself use index_delete.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON delete payload
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `namespace` (`string`, optional): Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces

Example input: `{"indexId":"<indexId>","payload":"<payload>","service":"vector"}`

### `upstashmcp_index_delete_namespace`

Delete Index Namespace · Destructive

PERMANENTLY deletes a namespace and everything in it — for a Search database, one of its named indexes. This cannot be undone. The default namespace cannot be deleted; empty it with index_reset instead.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `namespace` (`string`, required): The namespace to delete, or for Search the named index. Required — there is no default
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","namespace":"<namespace>","service":"vector"}`

### `upstashmcp_index_rename_namespace`

Rename Index Namespace · Destructive

Renames a namespace — for a Search database, one of its named indexes. The new name must not already be in use, and the default namespace cannot be renamed.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `namespace` (`string`, required): The namespace to rename, or for Search the named index
- `newNamespace` (`string`, required): The new name
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","namespace":"<namespace>","newNamespace":"<newNamespace>","service":"vector"}`

### `upstashmcp_index_reset`

Reset Index · Destructive

PERMANENTLY deletes every document in a namespace, leaving the empty namespace behind. Set allNamespaces to empty the whole index instead. This cannot be undone.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `allNamespaces` (`boolean`, optional): Empty every namespace of the index rather than one. Cannot be combined with namespace
- `namespace` (`string`, optional): Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_reset_credentials`

Reset Index Credentials · Destructive

Resets the REST token and read-only token of a Vector index or a Search database. Every client still using the old ones fails from that moment, so the user has to update their apps' environment variables. The new tokens are not in the result: fetch them with index_get and include_credentials: true. Confirm with the user before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","service":"vector"}`

### `upstashmcp_index_set_plan`

Change Index Plan · Destructive

Moves a Vector index or a Search database to another plan: payg (billed per request) or fixed (a flat monthly price). Search is billed as Vector, so one pricing page covers both: https://upstash.com/pricing/vector.md — its "Pay as You Go" is payg and "Fixed" is fixed; Pro is sold by sales. The current plan is type in index_get. Only an index already on a paid plan can switch; the API refuses a free one. This changes what the account is billed: tell the user the price from the pricing page and get their confirmation before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `plan` (`string`, required): The plan to move to. One of: `payg`, `fixed`.
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.

Example input: `{"indexId":"<indexId>","plan":"payg","service":"vector"}`

### `upstashmcp_index_update`

Update Index · Destructive

Updates one existing document in place, without re-sending the rest of it. Payload e.g. {"id":"a","metadata":{...},"metadataUpdateMode":"patch"} to merge into the existing metadata, or "overwrite" (the default) to replace it; may also carry vector, sparseVector or data to re-embed. Does nothing if the id does not exist — use vector_upsert or search_upsert to create.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON update payload
- `service` (`string`, required): Which product the index belongs to. A Vector index and a Search database are separate resources — the API returns 404 if this names the wrong one. One of: `vector`, `search`.
- `namespace` (`string`, optional): Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces

Example input: `{"indexId":"<indexId>","payload":"<payload>","service":"vector"}`

### `upstashmcp_qstash_flow_control_manage`

Manage QStash Flow Control · Destructive

Manages a flow-control key: pause, resume, pin (payload = pin options JSON), unpin (payload = unpin options JSON) or reset_rate.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): No description. One of: `pause`, `resume`, `pin`, `unpin`, `reset_rate`.
- `key` (`string`, required): Flow-control key
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `payload` (`string`, optional): JSON options for pin/unpin

Example input: `{"action":"pause","key":"<key>","region":"eu"}`

### `upstashmcp_qstash_manage_schedule`

Manage QStash Schedule · Destructive

Manages a QStash schedule: create (destinationUrl + cron required), get, delete, pause or resume (scheduleId required).

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): No description. One of: `create`, `get`, `delete`, `pause`, `resume`.
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `body` (`string`, optional): Message body for created schedules
- `cron` (`string`, optional): Cron expression, e.g. */5 * * * *
- `destinationUrl` (`string`, optional): No description.
- `scheduleId` (`string`, optional): The QStash schedule ID

Example input: `{"action":"create","region":"eu"}`

### `upstashmcp_qstash_reset_token`

Reset QStash Token · Destructive

Replaces a region's QStash token and read-only token without downtime, in two calls. QStash and Workflow share one QStash user per region, so every app publishing with QSTASH_TOKEN, and every Workflow client, needs the new token; the request signing keys are not changed. 1) Call without roll_to: resets nothing and returns the next token pair, which QStash already accepts alongside the current token (the same pair comes back until the roll). For Vercel marketplace users this also writes the next token to their Vercel env as QSTASH_TOKEN. 2) Once the user's apps run with next_token, call with roll_to set to it: that token becomes the current one and the old token stops working within seconds. If the roll fails, do not retry it: an earlier roll that timed out may have gone through (check with qstash_list_users and include_credentials: true), otherwise start over from step 1. Confirm with the user before rolling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `roll_to` (`string`, optional): The next_token from the first call, already deployed. Omit to get the next token pair

Example input: `{"region":"eu"}`

### `upstashmcp_qstash_set_budget`

Set QStash Budget · Destructive

Sets the monthly spending cap of a region's pay-as-you-go QStash user; fixed plans have none. Once the month's cost reaches the cap the bill stops growing and the user is rate limited. 0 removes the cap. Changing the budget, including to 0, lifts an active rate limit right away. A non-zero cap must be above what the user has already cost this month, and setting the value it already has fails with "budget already set". The current cap is budget in qstash_list_users. QStash and Upstash Workflow share one QStash user per region, so this covers both. Prices: https://upstash.com/pricing/qstash.md (Workflow: https://upstash.com/pricing/workflow.md). Confirm the amount with the user before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `budget` (`integer`, required): Monthly spending cap in whole US dollars: 0 removes the cap, otherwise 20 to 10000
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.

Example input: `{"budget":1,"region":"eu"}`

### `upstashmcp_qstash_set_plan`

Change QStash Plan · Destructive

Moves a region's QStash user to another plan: pay-as-you-go (billed per message) or a fixed monthly tier. QStash and Upstash Workflow share one QStash user per region, so this covers both. Prices: https://upstash.com/pricing/qstash.md (Workflow: https://upstash.com/pricing/workflow.md). On the pricing page "Pay as You Go" is payg, "Fixed 1M" is fixed_1m and "Fixed 10M" is fixed_10m. The current plan is type and reserved_type in qstash_list_users. The plan can change at most once an hour. This changes what the account is billed: tell the user the price from the pricing page and get their confirmation before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `plan` (`string`, required): The plan to move to. One of: `payg`, `fixed_1m`, `fixed_10m`.
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.

Example input: `{"plan":"payg","region":"eu"}`

### `upstashmcp_qstash_set_prod_pack`

Set QStash Prod Pack · Destructive

Enables or disables Prod Pack on a region's QStash user, a monthly add-on for pay-as-you-go and fixed plans that adds an uptime SLA, encryption at rest, SOC-2 compliance and Prometheus/Datadog metrics. QStash and Upstash Workflow share one QStash user per region, so this covers both. Prices: https://upstash.com/pricing/qstash.md (Workflow: https://upstash.com/pricing/workflow.md). Only accounts with a payment method can enable it, and asking for the state it is already in fails with "Prod Pack is already enabled/disabled". This changes what the account is billed: tell the user the price from the pricing page and get their confirmation before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `enabled` (`boolean`, required): true to enable Prod Pack, false to disable it
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.

Example input: `{"enabled":true,"region":"eu"}`

### `upstashmcp_redis_change_plan`

Change Redis Plan · Destructive

Moves an Upstash Redis database to another plan: pay-as-you-go (billed per command) or a fixed monthly tier. Prices and limits: https://upstash.com/pricing/redis.md — its "Pay as You Go" is payg and "Fixed 250MB" … "Fixed 500GB" are fixed_250mb … fixed_500gb. The current plan is the database's type and reserved_type in redis_get_database. A branch is always pay-as-you-go and refuses this. A database cannot be moved back to the free plan, and the plan can change at most once every 5 minutes. prod_pack and auto_upgrade can be set in the same call. This changes what the account is billed: tell the user the price from the pricing page and get their confirmation before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `plan` (`string`, required): The plan to move to. One of: `payg`, `fixed_250mb`, `fixed_1gb`, `fixed_5gb`, `fixed_10gb`, `fixed_50gb`, `fixed_100gb`, `fixed_500gb`.
- `auto_upgrade` (`boolean`, optional): Also enable or disable automatic plan upgrade; omit to leave it as it is
- `prod_pack` (`boolean`, optional): Also enable (true) or disable (false) Prod Pack; omit to leave it as it is

Example input: `{"databaseId":"<databaseId>","plan":"payg"}`

### `upstashmcp_redis_delete_database`

Delete Redis Database · Destructive

PERMANENTLY deletes an Upstash Redis database or branch and all of its data. This cannot be undone. A database that still has branches is refused until they are deleted; deleting a branch leaves its database untouched. Confirm the database name with the user before calling. When the client supports it, the server asks the user to type the name itself; otherwise the call needs confirm_name, set to the name the user confirmed, and without it nothing is deleted.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `confirm_name` (`string`, optional): The exact name of the resource, as the user confirmed it. Ask the user to confirm the name before setting this; never fill it in on your own. Ignored when the client can ask the user directly

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_rename_database`

Rename Redis Database · Destructive

Renames an Upstash Redis database or branch. A branch's name can use letters, numbers, hyphens, underscores and dots, starting and ending with a letter or number, and must be unique among the branches of its database.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `name` (`string`, required): The new database name (alphanumeric)

Example input: `{"databaseId":"<databaseId>","name":"<name>"}`

### `upstashmcp_redis_reset_credentials`

Reset Redis Credentials · Destructive

Resets an Upstash Redis database's password and REST tokens (read-write and read-only). Every client still using the old ones fails from that moment, so the user has to update their apps' environment variables. Refused for HIPAA-compliant databases and for databases whose credentials are managed as Vercel Marketplace environment variables. Also refused for a database with Protect Credentials enabled: its new password is shown only once, which this tool never does, so it would be lost; reset it in the Upstash console. The new credentials are not in the result: fetch them with redis_get_database and include_credentials: true. Confirm with the user before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `databaseId` (`string`, required): The Redis database ID

Example input: `{"databaseId":"<databaseId>"}`

### `upstashmcp_redis_run_command`

Run Redis Command · Destructive

Runs Redis commands directly on an Upstash Redis database over its REST API. No tokens needed — credentials are resolved server-side and never exposed. Not available for a database with Protect Credentials enabled (is_password_protected in redis_get_database): Upstash keeps no password for it. Each command is an array of strings, e.g. [["SET","key","value"],["GET","key"]]. One command runs directly; several run as a pipeline. Note for SCAN: reuse the returned cursor, and stop to ask the user if results get large.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `commands` (`array`, required): Redis commands, each as an array of strings
- `databaseId` (`string`, required): The Redis database ID

Example input: `{"commands":[],"databaseId":"<databaseId>"}`

### `upstashmcp_redis_set_auto_upgrade`

Set Redis Auto-Upgrade · Destructive

Enables or disables automatic plan upgrade for an Upstash Redis database.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `enabled` (`boolean`, required): true to enable auto-upgrade, false to disable

Example input: `{"databaseId":"<databaseId>","enabled":true}`

### `upstashmcp_redis_set_budget`

Set Redis Budget · Destructive

Sets the monthly spending cap of a pay-as-you-go Upstash Redis database; fixed plans have none. The month's bill never exceeds the cap. Below $1000 the database is also rate limited once the cap is reached; at $1000 and above it keeps serving at full speed. Email warnings go out at 70% and 90%. 0 removes the cap. Changing the budget, including to 0, lifts an active rate limit right away. A non-zero cap must be above what the database has already cost this month, and setting the value it already has fails with "budget already set". The current cap is budget in redis_get_database. How budgets work: https://upstash.com/pricing/redis.md. Confirm the amount with the user before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `budget` (`integer`, required): Monthly spending cap in whole US dollars: 0 removes the cap, otherwise 20 to 10000
- `databaseId` (`string`, required): The Redis database ID

Example input: `{"budget":1,"databaseId":"<databaseId>"}`

### `upstashmcp_redis_set_eviction`

Set Redis Eviction · Destructive

Enables or disables key eviction for an Upstash Redis database.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `enabled` (`boolean`, required): true to enable eviction, false to disable

Example input: `{"databaseId":"<databaseId>","enabled":true}`

### `upstashmcp_redis_set_prod_pack`

Set Redis Prod Pack · Destructive

Enables or disables Prod Pack on an Upstash Redis database: a per-database monthly add-on for pay-as-you-go and fixed plans that adds an uptime SLA, multi-zone high availability, encryption at rest, SOC-2 compliance and Prometheus/Grafana/Datadog metrics. Price and the full feature list: https://upstash.com/pricing/redis.md. Only accounts with a payment method can enable it. Not available on a branch. This changes what the account is billed: tell the user the price from the pricing page and get their confirmation before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `enabled` (`boolean`, required): true to enable Prod Pack, false to disable it

Example input: `{"databaseId":"<databaseId>","enabled":true}`

### `upstashmcp_redis_update_read_regions`

Update Redis Read Regions · Destructive

Replaces the read regions of a global Upstash Redis database with the given list: regions not in it are removed along with their replicas, new ones are added. Pass the full list (redis_get_database shows the current read_regions and primary_region); an empty list removes every read region. The primary region can't be a read region, a free database can have at most one, and the regions can change at most once every 30 minutes. Regional, HIPAA and Enterprise databases and branches are refused. Adding read regions costs more: on a fixed plan each one adds the plan's per-region price, and on pay-as-you-go every write is replicated to each read region and billed as another command, with storage counted in every region (https://upstash.com/pricing/redis.md). Confirm the regions and the cost with the user before calling.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `databaseId` (`string`, required): The Redis database ID
- `read_regions` (`array`, required): The complete list of read regions the database should have, e.g. ["us-west-2", "eu-central-1"]

Example input: `{"databaseId":"<databaseId>","read_regions":[]}`

### `upstashmcp_search_upsert`

Upsert Search Documents · Destructive

Upserts documents into a named index of a Search database (server-side embedding), creating the named index if it does not exist. Payload e.g. [{"id":"movie-1","content":{"title":"Star Wars"},"metadata":{...}}].

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `indexName` (`string`, required): The named index inside the Search database
- `payload` (`string`, required): JSON documents payload

Example input: `{"indexId":"<indexId>","indexName":"<indexName>","payload":"<payload>"}`

### `upstashmcp_vector_upsert`

Upsert Vectors · Destructive

Upserts vectors into a Vector index. Payload e.g. [{"id":"a","vector":[...],"metadata":{...}}] — or with useData=true, [{"id":"a","data":"text to embed"}]. For a Search database use search_upsert instead.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `indexId` (`string`, required): The Vector index ID, or the Search database ID
- `payload` (`string`, required): JSON payload as the Vector REST API expects
- `namespace` (`string`, optional): Namespace to write to (omit for the default namespace)
- `useData` (`boolean`, optional): true = /upsert-data (server-side embedding)

Example input: `{"indexId":"<indexId>","payload":"<payload>"}`

### `upstashmcp_workflow_manage_run`

Manage Workflow Run · Destructive

Operates on a Workflow run. To inspect a run by ID (its state, steps and errors, whether it has finished or not), use logs_list with service workflow and workflowRunId instead. get_steps is the narrower view: the live step state of a run that is still in progress. For a run that has finished or been cancelled, get_steps falls back to that run's log entry and says so. cancel asks QStash to stop the run and is asynchronous: the run moves to RUN_CANCELED in logs_list (service workflow) after a short delay, and the cancel call itself does not confirm that a run with this ID existed. Check logs_list, not get_steps, to verify a cancel.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): No description. One of: `get_steps`, `cancel`.
- `region` (`string`, required): QStash region of your QStash user. One of: `eu`, `us`.
- `workflowRunId` (`string`, required): The workflow run ID, which always starts with wfr_. A custom ID passed as workflowRunId when triggering is stored with that prefix (my-run-1 becomes wfr_my-run-1), and the prefix is required here. logs_list (service workflow) shows the exact IDs.

Example input: `{"action":"get_steps","region":"eu","workflowRunId":"<workflowRunId>"}`

## Related

Other Databases connectors ([all 39](/agentkit/connectors/?category=databases)):

- [AWS Redshift](/agentkit/connectors/redshift/): Scalekit connector, Trusted identity provider, 10 tools
- [Google BigQuery](/agentkit/connectors/bigquery/): Scalekit connector, OAuth, 47 tools
- [Airtable](/agentkit/connectors/airtable/): Scalekit connector, OAuth, 26 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
