The Get It DoneMCP Server

Get It Done ships a remote Model Context Protocol (MCP) server, so AI assistants like Claude and Cursor can work with your tasks directly — list them, read their full contents, create and update them, and even pull frames out of the videos attached to them.

Remote MCP · Streamable HTTP · https://app.nowgetitdone.com/api/mcp

Connect your assistant

The server speaks Streamable HTTP and authenticates every request with a Bearer token: a Get It Done API key, prefixed gid_. Any MCP client that supports remote servers can connect — no local install, no sidecar process.

Claude Code

claude mcp add --transport http getitdone https://app.nowgetitdone.com/api/mcp \
  --header "Authorization: Bearer gid_YOUR_API_KEY"

Claude Desktop, Cursor, or any remote-MCP client (JSON config)

{
  "mcpServers": {
    "getitdone": {
      "url": "https://app.nowgetitdone.com/api/mcp",
      "headers": {
        "Authorization": "Bearer gid_YOUR_API_KEY"
      }
    }
  }
}

API keys are per-user and shown once at creation. An in-app key management screen is on its way; for now, signed-in users mint keys through the authenticated POST /api/api-keys endpoint on their account.

7 tools, end to end

Everything an assistant needs to run a real task workflow — discovery, deep reads, and writes. The list below renders from the same catalog the server registers its tools from, so it is always exact.

Tool	Access	What it does
`list_workspaces`	Read	List the workspaces (organizations) the current user belongs to, with their ids. Pass a returned id as `workspaceId` on the other tools to target a specific workspace when the user has more than one.
`list_tasks`	Read	List tasks for the current user in their organization. Can filter by status and priority. Returns the latest version of each task.
`get_task_details`	Read	Get the FULL content of a single task: its rich-text notes and every attachment (image, video, document) with short-lived URLs the AI can fetch to read the actual content. Use this after list_tasks when you need to see what is inside a task. Identify the task by short ID (e.g. 123 for T-123) or task version ID.
`get_task_video_context`	Read	Pull visual context from a task's videos: extracts a few evenly-spaced frames from any uploaded video (screen recording etc.) in the task's notes or attachments so you can understand what it shows, and surfaces any YouTube/Vimeo links found in the notes. Use when a task references a video/screen recording. Identify the task by short ID (e.g. 123 for T-123) or task version ID.
`create_task`	Write	Create a new task for the current user in their organization.
`update_task`	Write	Update an existing task. You can update the name, status, priority, due date, notes, or story points. Identify the task by its short ID (e.g. T-123) or task version ID.
`archive_task`	Write	Archive or unarchive a task. Archived tasks are hidden from the main task list. Identify the task by its short ID (e.g. T-123).

Context other task tools don't give an AI

Most task-management MCP integrations stop at text and metadata. Get It Done treats the AI as a first-class user and hands it the same rich context a teammate would get:

Full task contents, attachments included

get_task_details returns a task's rich-text notes plus every attachment — images, videos, documents — each with a short-lived URL the assistant can fetch to read the actual content, not just a filename.

Video-frame extraction, server-side

get_task_video_context samples evenly-spaced frames from screen recordings and other videos attached to a task and returns them as images the AI can see — so "watch the bug repro and fix it" actually works. YouTube and Vimeo links in the notes are surfaced too.

MCP quota by plan

Every plan — including Free — can use the MCP server. Monthly API-call quotas come straight from the shared plan configuration:

Plan	MCP API calls / month
Free	50
Pro	50,000
Team	500,000

Full plan details on the pricing page.

Give your AI a task list

Create a free workspace, mint an API key, and point your assistant at the endpoint above.

Get started free