tldraw

MCP serverAI & models

tldraw is an MCP server that lets an AI agent draw and visually collaborate with you on a shared canvas. The agent can create and arrange shapes while you watch and edit the same drawing. It is useful when a task is easier to show than to describe in text.

Use tldraw in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add tldraw and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use tldraw to search

Details

Available today. Use it from your connected AI after setup.

Have an AI agent that can connect to MCP servers.

What your AI can do with it

  • Draw shapes on the tldraw canvas
  • Arrange and position shapes on the canvas
  • Collaborate visually with you on the same drawing
  • Work on a shared canvas alongside your agent

Getting started

  1. Have an AI agent that can connect to MCP servers.
  2. Add the tldraw MCP server to that agent's configuration.
  3. Open the tldraw canvas so you and the agent share the same drawing.
  4. Ask the agent to draw or arrange shapes and watch the canvas update.

Install tldraw

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user tldraw 'https://tldraw-mcp-app.tldraw.workers.dev/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://tldraw-mcp-app.tldraw.workers.dev/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=tldraw&config=eyJ1cmwiOiJodHRwczovL3RsZHJhdy1tY3AtYXBwLnRsZHJhdy53b3JrZXJzLmRldi9tY3AifQ==

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://tldraw-mcp-app.tldraw.workers.dev/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add tldraw --url 'https://tldraw-mcp-app.tldraw.workers.dev/mcp'

    Run it once, then sign in with codex mcp login tldraw if the server asks for an account.

From the project's README

As published by tldraw/tldraw in README.md. This repository publishes several servers, so only the opening is shown here.

Feature highlights

tldraw provides a feature-complete infinite canvas engine designed to be the foundation for any canvas app. Create custom shapes, tools, bindings and UI components for a custom experience. Use the default whiteboarding tool set or use the library's primitives to build entirely new shapes and interactions.

Shortened here. Read the whole README on GitHub.

Tools it offers (6)

What this server listed when Ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • search
  • exec
  • _exec_callback
  • _get_canvas_state
  • read_checkpoint
  • save_checkpoint

Signals

GitHub stars
51k
Forks
4k
Last commit
Sep 2026

Questions

What is the tldraw mcp server?
It is an MCP server that lets an AI agent draw and visually collaborate with you on tldraw's canvas, so the agent can create and arrange shapes while you work on the same drawing.
Can the agent draw on the canvas?
Yes. The agent can draw shapes and arrange them on the tldraw canvas, and you can collaborate visually on the same drawing.
Do I need to install anything besides the server?
You need an AI agent that can connect to MCP servers, and you need to add the tldraw MCP server to that agent's configuration.
Can I edit the drawing at the same time as the agent?
Yes. The canvas is shared, so you and the agent can collaborate visually on the same drawing.
Advanced
Delivery
tldraw MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-tldraw-tldraw
Source
github.com/tldraw/tldraw
Hosted endpoint
https://tldraw-mcp-app.tldraw.workers.dev/mcp