> **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 Stack.ai MCP server

The Stack.ai MCP connector routes your AI agent's tool calls to Stack.ai's own MCP server through Scalekit. Each user signs in to Stack.ai once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 32 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** AI, Automation, Developer Tools
**Tools:** 32: 20 read, 7 write, 5 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=STACKAIMCP)

## What you can do

- **Build AI projects**: create and edit projects from a plain-language description, import workflows, and validate them
- **Run projects**: execute published projects with inputs and review run history and per-step traces
- **Search knowledge bases**: list knowledge bases and pull the most relevant chunks for a query
- **Manage skills**: create, update, validate, and roll back skills and browse their version history
- **Upload files**: upload files for use as project inputs and get signed links to them
- **Review audit logs**: list who did what and when across the organization

## 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 Stack.ai MCP connection

   In **AgentKit > Connections**, create a Stack.ai MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

   Scalekit credentials are available for Stack.ai MCP server, so you don't need to register an OAuth app.

4. ### 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 = 'stackaimcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Stack.ai 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: 'stackaimcp_whoami',
     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 = "stackaimcp"
   identifier = "user_123"

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

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="stackaimcp_whoami",
       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: 'stackaimcp_audit_logs_list',
  toolInput: {},
  connector: 'stackaimcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="stackaimcp_audit_logs_list",
    tool_input={},
    connection_name="stackaimcp",
    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.

### `stackaimcp_audit_logs_list`

Audit Logs List · Read-only

List the active Stack AI organization's audit trail (who did what, when), with optional filters and pagination.

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

Inputs:

- `action` (`string`, optional): Filter by action verb (e.g. "export", "delete", "update", "run").
- `cursor` (`string`, optional): Opaque pagination cursor from a previous response's
pagination.next_cursor.
- `date_from` (`string`, optional): ISO-8601 lower bound (inclusive) on created_at.
- `date_to` (`string`, optional): ISO-8601 upper bound (inclusive) on created_at.
- `decision` (`string`, optional): Filter by decision ("allow" / "deny").
- `page_size` (`string`, optional): Maximum entries per page (clamped to 200).
- `permission_key` (`string`, optional): Filter by permission key (e.g. "org.members.remove").
- `resource_type` (`string`, optional): Filter by resource type (e.g. "projects").
- `search` (`string`, optional): Free-text search across the entry.
- `user_id` (`string`, optional): Filter to a single acting member's id.

Example input: `{}`

### `stackaimcp_get_project`

Get Project · Read-only

Retrieve a project's node and edge graph as a paginated, self-contained subgraph with connectivity preserved across pages.

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

Inputs:

- `project_id` (`string`, required): Project ID (from ``projects_list``).
- `cursor` (`string`, optional): Opaque pagination token from a prior response's
``pagination.next_cursor``. Pass ``null`` to fetch
the first page.
- `page_size` (`string`, optional): Maximum nodes per page. Defaults to 50, clamped
to [1, 200].
- `verbose` (`string`, optional): When true, also include the raw upstream
``flow`` object verbatim. Off by default to avoid
duplicating graph data. Refused with a structured
``flow_too_large`` error (carrying ``next_action`` and
node/edge counts) when ``nodes + edges`` exceeds the
server's ``max_inline_flow_elements`` cap; in that
case page through the flow using ``next_cursor``
instead.
- `version` (`string`, optional): ``"published"`` (default — falls back to draft if
none) or ``"draft"`` to read the draft directly.

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

### `stackaimcp_get_project_corrections`

Get Project Corrections · Read-only

Re-validate a project draft and return paginated correction entries for params cleaned up during creation or editing.

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

Inputs:

- `project_id` (`string`, required): Project ID to re-validate.
- `cursor` (`string`, optional): Opaque pagination cursor from a prior response.
- `page_size` (`string`, optional): Maximum corrections per page (clamped to 200).

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

### `stackaimcp_get_run`

Get Run · Read-only

Fetch the per-node execution trace for a project run, filtered by severity and optionally expanded with inputs and outputs.

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

Inputs:

- `project_id` (`string`, required): Project (flow) ID the run belongs to.
- `run_id` (`string`, required): Run ID to fetch.
- `cursor` (`string`, optional): Opaque pagination cursor from a previous response's
``pagination.next_cursor``.
- `expand` (`string`, optional): Optional list of node ids whose ``inputs`` /
``outputs`` should be populated. Up to 50 ids per call.
Ids not in the current page are surfaced in the summary.
- `page_size` (`string`, optional): Maximum nodes per page (clamped to 200).
- `severity_filter` (`string`, optional): Which nodes to return:
``"failed_or_slow"`` (default), ``"failed"``,
``"slow"``, or ``"all"``.
- `verbose` (`string`, optional): When true, include every node-in-page's
inputs/outputs. Use ``expand`` for finer grain.

Example input: `{"project_id":"<project_id>","run_id":"<run_id>"}`

### `stackaimcp_list_connections`

List Connections · Read-only

List the OAuth and API-key connections the authenticated user has configured in Stack AI.

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

Inputs:

- `cursor` (`string`, optional): Opaque pagination cursor from a previous response's
``pagination.next_cursor``.
- `page_size` (`string`, optional): Maximum connections per page (clamped to 200).
- `provider_id` (`string`, optional): Optional filter, e.g. ``"gmail"``, ``"slack"``.
Pass null for all.

Example input: `{}`

### `stackaimcp_list_knowledge_bases`

List Knowledge Bases · Read-only

List knowledge bases available to the authenticated user, with optional verbose metadata.

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

Inputs:

- `cursor` (`string`, optional): Pagination cursor from a previous response.
- `page_size` (`string`, optional): Maximum results per page (clamped to 200).
- `verbose` (`string`, optional): When true, return the full KB metadata for each
row instead of the compact projection.

Example input: `{}`

### `stackaimcp_list_projects`

List Projects · Read-only

Fetch a paginated list of projects accessible to the authenticated account.

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

Inputs:

- `cursor` (`string`, optional): Opaque pagination cursor from a previous response.
Pass ``null`` to fetch the first page.
- `owned_only` (`string`, optional): When true, only return projects the user owns.
- `page_size` (`string`, optional): Maximum number of projects per page. Defaults to
50, clamped to [1, 200].

Example input: `{}`

### `stackaimcp_list_providers_actions`

List Providers Actions · Read-only

List available Stack AI integration providers and their actions, with optional full schemas for specific action IDs.

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

Inputs:

- `expand` (`string`, optional): optional list of action / trigger ids to drill into;
only valid with a single ``provider_id`` string.
- `include_deprecated` (`string`, optional): When true, surface deprecated providers /
actions / triggers instead of filtering them. Off by default.
- `provider_id` (`string`, optional): ``null``, a single id (e.g. ``"gmail"``), or a list
(e.g. ``["gmail", "slack"]``).

Example input: `{}`

### `stackaimcp_list_triggers`

List Triggers · Read-only

List the cron, polling, and webhook triggers configured on a specific project.

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

Inputs:

- `project_id` (`string`, required): Project (flow) ID to inspect.
- `verbose` (`string`, optional): When true, return the full trigger metadata
instead of the compact projection.

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

### `stackaimcp_projects_validate_flow_json`

Projects Validate Flow Json · Read-only

Run Stack AI's pre-flight validators against a raw flow JSON payload without saving it as a project.

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

Inputs:

- `flow_json` (`object`, required): Object with nodes and edges arrays, in the shape
returned by projects_get.
- `cursor` (`string`, optional): Opaque pagination cursor from a prior response.
- `page_size` (`string`, optional): Maximum findings per page (clamped to 200).
- `severity_filter` (`string`, optional): "all" (default) or "errors_only".

Example input: `{"flow_json":{}}`

### `stackaimcp_runs_list`

Runs List · Read-only

List a Stack AI project's run history, paginated.

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

Inputs:

- `project_id` (`string`, required): Project id whose runs to list.
- `cursor` (`string`, optional): Opaque pagination cursor from a previous response.
- `page_size` (`string`, optional): Maximum rows per page. Defaults to 25, clamped
to [1, 200].

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

### `stackaimcp_search_kb`

Search Kb · Read-only

Search a Stack AI knowledge base and return the top matching chunks ranked by relevance.

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

Inputs:

- `kb_id` (`string`, required): Knowledge base ID to search.
- `query` (`string`, required): Natural-language search query (must be non-empty).
- `expand` (`string`, optional): Optional list of ``chunk_id`` values whose
full ``text`` should be populated in the response. Other
chunks still come back with preview only. Up to 20 ids
per call; ids that don't match any chunk in the current
result set are surfaced in the summary.
- `query_strategy` (`string`, optional): Retrieval mode: ``"semantic"`` (embedding
similarity, default), ``"keyword"`` (BM25), or ``"hybrid"``
(rerank of both).
- `top_k` (`string`, optional): Maximum chunks to return. Defaults to 5, clamped to
[1, 20] (the upstream cap).

Example input: `{"kb_id":"<kb_id>","query":"<query>"}`

### `stackaimcp_server_info`

Server Info · Read-only

Return the Stack AI MCP server's version, mode, and capability flags.

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

Inputs: none.

Example input: `{}`

### `stackaimcp_skills_get`

Skills Get · Read-only

Fetch one Stack AI skill's full detail: instructions, frontmatter, actions, and file manifest.

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

Inputs:

- `skill_id` (`string`, required): The skill id (from skills_list).

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

### `stackaimcp_skills_list`

Skills List · Read-only

List the Stack AI skills visible to the authenticated user, builtins first.

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

Inputs:

- `cursor` (`string`, optional): Opaque pagination cursor from a previous response's
pagination.next_cursor. Pass null to fetch the first page.
- `page_size` (`string`, optional): Maximum skills per page. Defaults to 25, clamped
to [1, 100].

Example input: `{}`

### `stackaimcp_skills_validate`

Skills Validate · Read-only

Validate a proposed Stack AI skill bundle offline and preview the normalization the write tools would apply.

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

Inputs:

- `files` (`array`, required): The file bundle: a list of ``{ path, content_base64 }``
objects. ``path`` is the relative POSIX path inside the bundle; a root
``SKILL.md`` (exact case) is required.
- `actions` (`string`, optional): Optional provider_id.action_id refs to check (format only)
and merge into the normalization preview.

Example input: `{"files":[]}`

### `stackaimcp_skills_version_get`

Skills Version Get · Read-only

Fetch one historical version of a Stack AI skill's full detail: instructions, frontmatter, actions, and file manifest.

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

Inputs:

- `skill_id` (`string`, required): The skill id (from skills_list).
- `version` (`integer`, required): The version number to fetch (1-based, from
skills_versions_list).

Example input: `{"skill_id":"<skill_id>","version":1}`

### `stackaimcp_skills_versions_list`

Skills Versions List · Read-only

List a Stack AI skill's full version history, newest first.

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

Inputs:

- `skill_id` (`string`, required): The skill id (from skills_list).

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

### `stackaimcp_validate_workflow`

Validate Workflow · Read-only

Run pre-flight validation checks on a project draft and return paginated errors and warnings with stable codes and fix hints.

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

Inputs:

- `project_id` (`string`, required): Project ID to validate. The validator
always reads the draft, not the published version.
- `cursor` (`string`, optional): Opaque pagination cursor from a prior response.
- `page_size` (`string`, optional): Maximum findings per page (clamped to 200).
- `severity_filter` (`string`, optional): ``"all"`` (default) returns errors AND
warnings; ``"errors_only"`` drops warnings so an LLM
checking "can I run this?" doesn't have to wade
through nice-to-haves.

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

### `stackaimcp_whoami`

Whoami · Read-only

Return the authenticated user's profile, active organization, plan, and paginated list of all organizations.

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

Inputs:

- `cursor` (`string`, optional): Opaque pagination cursor from a previous response's
``pagination.next_cursor``. Pass null to start.
- `page_size` (`string`, optional): Maximum orgs per page. Defaults to 50, clamped
to [1, 200].

Example input: `{}`

### `stackaimcp_create_project`

Create Project · Write

Create a new Stack AI project from a natural-language description by generating its nodes and edges with AI assistance.

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

Inputs:

- `description` (`string`, required): High-level description of what the project should do.

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

### `stackaimcp_files_create_upload_url`

Files Create Upload Url · Write

Request a presigned PUT URL from Stack AI so the client can upload a large file out of band.

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

Inputs:

- `byte_length` (`integer`, required): Exact byte count of the file (1..104857600).
- `content_hash` (`string`, required): Base64-encoded SHA-256 of the file's bytes
(44 characters, ending in "=").
- `filename` (`string`, required): Display name (e.g. invoice.pdf).
- `mime_type` (`string`, optional): Optional Content-Type hint. Defaults to
Stack AI's inference from the filename when omitted.
- `purpose` (`string`, optional): Storage bucket. Defaults to "user-documents".

Example input: `{"byte_length":1,"content_hash":"<content_hash>","filename":"<filename>"}`

### `stackaimcp_files_finalize_upload`

Files Finalize Upload · Write

Finalize a presigned Stack AI file upload and return a projects_run-ready signed URL.

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

Inputs:

- `file_id` (`string`, required): The file_id returned by files_create_upload_url.

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

### `stackaimcp_files_upload`

Files Upload · Write

Upload a file inline as base64 to Stack AI and return a signed URL usable in project inputs.

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

Inputs:

- `content_base64` (`string`, required): Standard-alphabet base64 of the bytes.
- `filename` (`string`, required): Display name (e.g. invoice.pdf). Used for
Content-Disposition and the storage key.
- `mime_type` (`string`, optional): Optional Content-Type hint. Defaults to
application/octet-stream.
- `purpose` (`string`, optional): Storage bucket. Defaults to "user-documents",
which is what projects_run doc-* inputs expect.

Example input: `{"content_base64":"<content_base64>","filename":"<filename>"}`

### `stackaimcp_projects_import`

Projects Import · Write

Create a new draft Stack AI project from an exported workflow JSON.

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

Inputs:

- `workflow_json` (`object`, required): Parsed export object. Must be JSON-safe.
Pass the parsed body, not a string blob.
- `folder_id` (`string`, optional): Optional folder where the new project should
land. Null lets Stack AI pick the default.
- `project_name` (`string`, optional): Optional name for the new project. When
omitted, the name embedded in the export is used.

Example input: `{"workflow_json":{}}`

### `stackaimcp_skills_create`

Skills Create · Write

Create a new Stack AI skill (version 1) from text fields or a file bundle.

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

Inputs:

- `actions` (`string`, optional): Optional action refs the skill may invoke, each
provider_id.action_id. Pass null for none.
- `description` (`string`, optional): A one-line description of when to use the skill
(text mode only).
- `files` (`string`, optional): Optional file bundle (file mode): a list of
``{ path, content_base64 }`` objects with a root ``SKILL.md``.
- `instructions` (`string`, optional): The SKILL.md body, markdown (text mode only).
- `name` (`string`, optional): The skill name, unique within the org (text mode
only).

Example input: `{}`

### `stackaimcp_switch_org`

Switch Org · Write

Set the active organization for the current session, routing all subsequent org-scoped tools to that org.

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

Inputs:

- `org_id` (`string`, required): The Stack AI organization id to activate. Find valid
ids by calling ``whoami``.

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

### `stackaimcp_edit_project`

Edit Project · Destructive

Edit an existing Stack AI project using a natural-language description or a structured patch of node and edge operations.

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

Inputs:

- `project_id` (`string`, required): No description.
- `description` (`string`, optional): No description.
- `direct_patch` (`string`, optional): No description.
- `dry_run` (`string`, optional): Pass true together with ``direct_patch`` to validate the
patch without saving. Shows projected node/edge counts and
delta; ``published`` is always false for a dry run.
- `publish` (`string`, optional): No description.

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

### `stackaimcp_projects_edit_ui`

Projects Edit Ui · Destructive

Patch a Stack AI project's UI options (theme, welcome message, allowed origins, etc.) without modifying its flow graph.

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

Inputs:

- `project_id` (`string`, required): Project id whose UI options to update.
- `updates` (`object`, required): Object of UI option fields to merge. At least one
key required. Unknown keys raise an error with the list
of bad keys.
- `publish` (`string`, optional): Publish the new draft on success. Defaults to false.

Example input: `{"project_id":"<project_id>","updates":{}}`

### `stackaimcp_run_project`

Run Project · Destructive

Execute a published Stack AI project by supplying a key-value inputs map that matches the flow's declared input schema.

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

Inputs:

- `inputs` (`object`, required): No description.
- `project_id` (`string`, required): No description.
- `verbose` (`string`, optional): No description.
- `version` (`string`, optional): No description.

Example input: `{"inputs":{},"project_id":"<project_id>"}`

### `stackaimcp_skills_rollback`

Skills Rollback · Destructive

Restore a prior version of a Stack AI skill's content by publishing it as a new latest version.

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

Inputs:

- `skill_id` (`string`, required): The skill id to roll back (from skills_list).
- `version` (`integer`, required): The historical version whose content to restore
(1-based, from skills_versions_list). It must not
be the current latest version.

Example input: `{"skill_id":"<skill_id>","version":1}`

### `stackaimcp_skills_update`

Skills Update · Destructive

Publish a new version of a Stack AI skill as a full replacement, from text fields or a file bundle.

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

Inputs:

- `skill_id` (`string`, required): The skill id to update (from skills_list).
- `actions` (`string`, optional): The full replacement list of provider_id.action_id
refs. Pass null for none - this clears any existing refs,
so re-send the current list to keep them.
- `description` (`string`, optional): The full replacement description (text mode
only).
- `files` (`string`, optional): Optional file bundle (file mode): a list of
``{ path, content_base64 }`` objects with a root ``SKILL.md``.
- `instructions` (`string`, optional): The full replacement SKILL.md body, markdown
(text mode only).
- `name` (`string`, optional): The skill name (text mode only) - re-send the current
one unless you rename it.

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

## Related

Other AI connectors ([all 153](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 69 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 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 |
