Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the Upstash MCP server

Vendor MCP
Open markdown

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.

Tools
77
What they doRead · write · destructive
28 · 9 · 4028 read9 write40 destructive
Users sign in with
OAuth app
Your own Upstash MCP server app

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv
  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .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.

  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

    quickstart.mts
    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)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • upstashmcp_blob_download_urlMints 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.Read-only

    Get Blob Download URL

    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.

    Inputs

    bucket_idstringrequired
    The bucket's id, from blob_bucket list or create
    filesarrayrequired
    The objects to mint download URLs for, one entry each
    expires_ininteger
    How long the URLs live, in seconds (default and maximum 600, the lifetime of the credential that signs them)
  • upstashmcp_box_accountAccount-wide views across every box.Read-only

    Get Box Account

    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).

    Inputs

    actionstringrequired
    The action to performone of summarybillinglogs
    end_timeinteger
    Unix seconds
    levelstring
    No description.one of infowarnerror
    limitinteger
    No description.
    offsetinteger
    No description.
    searchstring
    No description.
    sourcestring
    No description.
    start_timeinteger
    Unix seconds
    statusstring
    Which boxes to summarise (summary, default: active)one of activedeleted
  • upstashmcp_box_logsReads a box's timestamped log entries — system, user and agent sources — which is how to find out what happened inside it.Read-only

    Get Box Logs

    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.

    Inputs

    box_idstringrequired
    The box ID (its name works too)
    end_timeinteger
    Only entries at or before this Unix timestamp (seconds)
    levelstring
    Only entries at this levelone of infowarnerror
    limitinteger
    Maximum entries to return (max 1000, default 100)
    offsetinteger
    Entries to skip, for paging (default 0)
    searchstring
    Only entries whose message matches this text
    sourcestring
    Only entries from this sourceone of systemuseragent
    start_timeinteger
    Only entries at or after this Unix timestamp (seconds)
  • upstashmcp_box_metricsResource and token usage for a box.Read-only

    Get Box Metrics

    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).

    Inputs

    actionstringrequired
    The action to performone of currenthistorytokensstepsstep_diff
    box_idstringrequired
    The box ID (its name works too)
    daysinteger
    Days of token usage to cover
    rangestring
    Time span for history, e.g. 1h, 24h, 7d
    shastring
    Step commit (step_diff)
    stepstring
    Resolution for history, e.g. 1m, 5m, 1h
  • upstashmcp_console_redis_keysConsole only: one SCAN page of a Redis database with each key's type and TTL.Read-only

    List Redis Keys (Console)

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

    Inputs

    databaseIdstringrequired
    The Redis database ID
    countinteger
    No description.default 100
    cursorstring
    No description.default 0
    matchstring
    No description.
    typestring
    Only keys of this type (SCAN's TYPE option)one of stringhashlistsetzsetstreamjson
  • upstashmcp_console_redis_valueConsole only: one Redis key's type, TTL, size and a bounded read of its value.Read-only

    Read Redis Value (Console)

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

    Inputs

    databaseIdstringrequired
    The Redis database ID
    keystringrequired
    No description.
  • upstashmcp_dlq_listLists the dead-letter queue for QStash messages or Workflow runs (service picks which).Read-only

    List Dead Letter Queue

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

    Inputs

    regionstringrequired
    QStash region of your QStash userone of euus
    servicestringrequired
    Which service the operation targets: plain QStash messaging or Upstash Workflowone of qstashworkflow
    cursorstring
    No description.
  • upstashmcp_index_fetchFetches documents by ID.Read-only

    Fetch Index Documents

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

    Inputs

    indexIdstringrequired
    The Vector index ID, or the Search database ID
    payloadstringrequired
    JSON fetch payload
    servicestringrequired
    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 oneone of vectorsearch
    namespacestring
    Vector: the namespace (omit for the default one). Search: the named index, which is required — list them with index_list_namespaces