Loops MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

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. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_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)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'loopsmcp_get_loop_queue',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_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)

What you can do

Connect this agent connector to let your agent:

• Update task, bulk — Update a task’s title, body, status, priority, due date, or loop assignment
• Loop ship, reopen, close — Mark a loop as shipped and notify all members via email
• Priority set loop — Set the numeric priority of a loop in the work queue (lower number = higher priority)
• Loops reorder — Bulk reorder loops in the work queue by passing an array of loop IDs in the desired priority order
• List tasks, loops — List unassigned tasks in the workspace, optionally filtered by status or priority
• Get workspace, workflow, task — Get workspace details including the AI context (project-level agent instructions)

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

loopsmcp_bulk_update_tasks # Bulk update the status or priority of multiple tasks at once. 4 params ▾

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

Name Type Required Description

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

status string optional New status for all tasks

loopsmcp_close_loop # Put a loop on hold, pausing work without permanently closing it. 1 param ▾

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

Name Type Required Description

loop_id string required The loop ID (ULID format)

loopsmcp_create_loop # Create a new loop to group related tasks into a development cycle. 4 params ▾

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

Name Type Required Description

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"

loopsmcp_create_loop_from_tasks # Create a new loop and assign a set of existing tasks to it in one operation. 3 params ▾

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

Name Type Required Description

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

loopsmcp_create_task # Create a new task in the workspace with an optional title, body, priority, and loop assignment. 4 params ▾

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

Name Type Required Description

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)

loopsmcp_delete_task # Permanently delete a task by its ID. This action cannot be undone. 1 param ▾

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

Name Type Required Description

task_id string required The task ID (ULID format)

loopsmcp_get_loop # Get a single loop with all its assigned tasks, comments, and AI context. 1 param ▾

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

Name Type Required Description

loop_id string required The loop ID (ULID format)

loopsmcp_get_loop_queue # Get the priority-ordered loop queue for the workspace. 0 params ▾

Get the priority-ordered loop queue for the workspace.

loopsmcp_get_next_work # Get the highest-priority loop with approved tasks ready for implementation. 0 params ▾

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

loopsmcp_get_queue_stats # Get work queue statistics for the workspace, including counts of loops with work ready. 0 params ▾

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

loopsmcp_get_task # Get a single task with its full agent prompt (body) and all comments. 1 param ▾

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

Name Type Required Description

task_id string required The task ID (ULID format)

loopsmcp_get_workflow # Get step-by-step instructions for a named Loops workflow (triage, organize, implement, or manage). 1 param ▾

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

Name Type Required Description

workflow string required Which workflow: triage, organize, implement, or manage

loopsmcp_get_workspace # Get workspace details including the AI context (project-level agent instructions). 0 params ▾

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

loopsmcp_list_loops # List all loops in the workspace with task counts, statuses, and AI context. 0 params ▾

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

loopsmcp_list_tasks # List unassigned tasks in the workspace, optionally filtered by status or priority. 2 params ▾

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

Name Type Required Description

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

loopsmcp_reopen_loop # Reopen an on-hold loop, returning it to the active queue. 1 param ▾

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

Name Type Required Description

loop_id string required The loop ID (ULID format)

loopsmcp_reorder_loops # Bulk reorder loops in the work queue by passing an array of loop IDs in the desired priority order. 1 param ▾

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

Name Type Required Description

loop_ids array required Array of loop IDs in priority order (first = highest priority)

loopsmcp_set_loop_priority # Set the numeric priority of a loop in the work queue (lower number = higher priority). 2 params ▾

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

Name Type Required Description

loop_id string required The loop ID (ULID format)

priority number required The priority value (0 = highest priority)

loopsmcp_ship_loop # Mark a loop as shipped and notify all members via email. 1 param ▾

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

Name Type Required Description

loop_id string required The loop ID (ULID format)

loopsmcp_update_task # Update a task's title, body, status, priority, due date, or loop assignment. 7 params ▾

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

Name Type Required Description

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

status string optional New status: approved (approve for implementation), rejected (decline), in_progress (being worked on), shipped (done), on_hold (paused)

title string optional New task title