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.

NameTypeRequiredDescription

task_idsarrayrequiredArray of task IDs to update

loop_idstringoptionalLoop ID to assign all tasks to (null to unassign)

prioritystringoptionalNew priority for all tasks

statusstringoptionalNew 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.

NameTypeRequiredDescription

loop_idstringrequiredThe 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.

NameTypeRequiredDescription

namestringrequiredLoop name (e.g., "v2 Auth Refactor", "Payment Bug Fixes")

ai_contextstringoptionalAgent instructions for this loop: scope, constraints, architecture decisions, specific requirements. This is shown to implementing agents alongside each task.

descriptionstringoptionalHuman-readable description of the loop

visibilitystringoptionalVisibility: "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.

NameTypeRequiredDescription

loop_namestringrequiredName for the new loop

task_idsarrayrequiredArray of task IDs to assign to the new loop

loop_descriptionstringoptionalDescription 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.

NameTypeRequiredDescription

titlestringrequiredTask title — a concise summary of what needs to be done

bodystringoptionalAgent prompt: detailed instructions for the AI agent that will implement this task. Include specific requirements, acceptance criteria, and any context needed.

loop_idstringoptionalOptional loop ID to assign the task to immediately

prioritystringoptionalTask 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.

NameTypeRequiredDescription

task_idstringrequiredThe 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.

NameTypeRequiredDescription

loop_idstringrequiredThe 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.

NameTypeRequiredDescription

task_idstringrequiredThe 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).

NameTypeRequiredDescription

workflowstringrequiredWhich 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.

NameTypeRequiredDescription

prioritystringoptionalFilter by priority: none, low, medium, high, urgent

statusstringoptionalFilter 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.

NameTypeRequiredDescription

loop_idstringrequiredThe 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.

NameTypeRequiredDescription

loop_idsarrayrequiredArray 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).

NameTypeRequiredDescription

loop_idstringrequiredThe loop ID (ULID format)

prioritynumberrequiredThe 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.

NameTypeRequiredDescription

loop_idstringrequiredThe 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.

NameTypeRequiredDescription

task_idstringrequiredThe task ID (ULID format)

bodystringoptionalNew agent prompt (implementation instructions)

due_datestringoptionalDue date in YYYY-MM-DD format (null to clear)

loop_idstringoptionalLoop ID to assign to (null to unassign from loop)

prioritystringoptionalNew priority

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

titlestringoptionalNew task title