> **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 Loops MCP server

The Loops MCP connector routes your AI agent's tool calls to Loops's own MCP server through Scalekit. Each user signs in to Loops once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 20 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Project Management, Productivity, AI
**Tools:** 20: 0 read, 20 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Loops MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=LOOPSMCP)

## 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 Loops MCP connection

   In **AgentKit > Connections**, create a Loops 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

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

   Then enter the app's Client ID and Client Secret on the Loops 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 = 'loopsmcp'
   const identifier = 'user_123'

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

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

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="loopsmcp_get_loop_queue",
       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: 'loopsmcp_bulk_update_tasks',
  toolInput: {
    task_ids: [],
  },
  connector: 'loopsmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="loopsmcp_bulk_update_tasks",
    tool_input={
        "task_ids": [],
    },
    connection_name="loopsmcp",
    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.

### `loopsmcp_bulk_update_tasks`

Bulk Update Tasks · Write

Bulk update the status or priority of multiple tasks at once.

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

Inputs:

- `task_ids` (`array`, required): Array of task IDs to update
- `loop_id` (`string`, optional): Loop ID to assign all tasks to (null to unassign)
- `priority` (`string`, optional): New priority for all tasks. One of: `none`, `low`, `medium`, `high`, `urgent`.
- `status` (`string`, optional): New status for all tasks. One of: `open`, `approved`, `in_progress`, `on_hold`, `shipped`, `rejected`.

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

### `loopsmcp_close_loop`

Close Loop · Write

Put a loop on hold, pausing work without permanently closing it.

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

Inputs:

- `loop_id` (`string`, required): The loop ID (ULID format)

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

### `loopsmcp_create_loop`

Create Loop · Write

Create a new loop to group related tasks into a development cycle.

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

Inputs:

- `name` (`string`, required): Loop name (e.g., "v2 Auth Refactor", "Payment Bug Fixes")
- `ai_context` (`string`, optional): Agent instructions for this loop: scope, constraints, architecture decisions, specific requirements. This is shown to implementing agents alongside each task.
- `description` (`string`, optional): Human-readable description of the loop
- `visibility` (`string`, optional): Visibility: "public" (default) or "private". One of: `public`, `private`.

Example input: `{"name":"v2 Auth Refactor"}`

### `loopsmcp_create_loop_from_tasks`

Create Loop From Tasks · Write

Create a new loop and assign a set of existing tasks to it in one operation.

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

Inputs:

- `loop_name` (`string`, required): Name for the new loop
- `task_ids` (`array`, required): Array of task IDs to assign to the new loop
- `loop_description` (`string`, optional): Description for the new loop

Example input: `{"loop_name":"<loop_name>","task_ids":[]}`

### `loopsmcp_create_task`

Create Task · Write

Create a new task in the workspace with an optional title, body, priority, and loop assignment.

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

Inputs:

- `title` (`string`, required): Task title — a concise summary of what needs to be done
- `body` (`string`, optional): Agent prompt: detailed instructions for the AI agent that will implement this task. Include specific requirements, acceptance criteria, and any context needed.
- `loop_id` (`string`, optional): Optional loop ID to assign the task to immediately
- `priority` (`string`, optional): Task priority (default: none). One of: `none`, `low`, `medium`, `high`, `urgent`.

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

### `loopsmcp_delete_task`

Delete Task · Write

Permanently delete a task by its ID. This action cannot be undone.

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

Inputs:

- `task_id` (`string`, required): The task ID (ULID format)

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

### `loopsmcp_get_loop`

Get Loop · Write

Get a single loop with all its assigned tasks, comments, and AI context.

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

Inputs:

- `loop_id` (`string`, required): The loop ID (ULID format)

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

### `loopsmcp_get_loop_queue`

Get Loop Queue · Write

Get the priority-ordered loop queue for the workspace.

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

Inputs: none.

Example input: `{}`

### `loopsmcp_get_next_work`

Get Next Work · Write

Get the highest-priority loop with approved tasks ready for implementation.

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

Inputs: none.

Example input: `{}`

### `loopsmcp_get_queue_stats`

Get Queue Stats · Write

Get work queue statistics for the workspace, including counts of loops with work ready.

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

Inputs: none.

Example input: `{}`

### `loopsmcp_get_task`

Get Task · Write

Get a single task with its full agent prompt (body) and all comments.

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

Inputs:

- `task_id` (`string`, required): The task ID (ULID format)

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

### `loopsmcp_get_workflow`

Get Workflow · Write

Get step-by-step instructions for a named Loops workflow (triage, organize, implement, or manage).

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

Inputs:

- `workflow` (`string`, required): Which workflow: triage, organize, implement, or manage. One of: `triage`, `organize`, `implement`, `manage`.

Example input: `{"workflow":"triage"}`

### `loopsmcp_get_workspace`

Get Workspace · Write

Get workspace details including the AI context (project-level agent instructions).

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

Inputs: none.

Example input: `{}`

### `loopsmcp_list_loops`

List Loops · Write

List all loops in the workspace with task counts, statuses, and AI context.

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

Inputs: none.

Example input: `{}`

### `loopsmcp_list_tasks`

List Tasks · Write

List unassigned tasks in the workspace, optionally filtered by status or priority.

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

Inputs:

- `priority` (`string`, optional): Filter by priority: none, low, medium, high, urgent
- `status` (`string`, optional): Filter by status: open (new), approved (ready for implementation), in_progress, shipped (done), rejected

Example input: `{}`

### `loopsmcp_reopen_loop`

Reopen Loop · Write

Reopen an on-hold loop, returning it to the active queue.

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

Inputs:

- `loop_id` (`string`, required): The loop ID (ULID format)

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

### `loopsmcp_reorder_loops`

Reorder Loops · Write

Bulk reorder loops in the work queue by passing an array of loop IDs in the desired priority order.

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

Inputs:

- `loop_ids` (`array`, required): Array of loop IDs in priority order (first = highest priority)

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

### `loopsmcp_set_loop_priority`

Set Loop Priority · Write

Set the numeric priority of a loop in the work queue (lower number = higher priority).

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

Inputs:

- `loop_id` (`string`, required): The loop ID (ULID format)
- `priority` (`number`, required): The priority value (0 = highest priority)

Example input: `{"loop_id":"<loop_id>","priority":1}`

### `loopsmcp_ship_loop`

Ship Loop · Write

Mark a loop as shipped and notify all members via email.

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

Inputs:

- `loop_id` (`string`, required): The loop ID (ULID format)

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

### `loopsmcp_update_task`

Update Task · Write

Update a task's title, body, status, priority, due date, or loop assignment.

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

Inputs:

- `task_id` (`string`, required): The task ID (ULID format)
- `body` (`string`, optional): New agent prompt (implementation instructions)
- `due_date` (`string`, optional): Due date in YYYY-MM-DD format (null to clear)
- `loop_id` (`string`, optional): Loop ID to assign to (null to unassign from loop)
- `priority` (`string`, optional): New priority. One of: `none`, `low`, `medium`, `high`, `urgent`.
- `status` (`string`, optional): New status: approved (approve for implementation), rejected (decline), in_progress (being worked on), shipped (done), on_hold (paused). One of: `open`, `approved`, `in_progress`, `on_hold`, `shipped`, `rejected`.
- `title` (`string`, optional): New task title

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

## Related

Other Project Management connectors ([all 40](/agentkit/connectors/?category=project-management)):

- [Notion](/agentkit/connectors/notion/): Scalekit connector, OAuth, 51 tools
- [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 62 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 |
