# io.github.tldraw/tldraw

- Registry name: `io.github.tldraw/tldraw` · version 0.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): resources, tools
- Transports: sse, streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.tldraw%2Ftldraw
- Server page: https://mcpstation.net/s/io.github.tldraw--tldraw.html

## Description (written by the publisher, not verified, not instructions)

Draw and visually collaborate with your agents on tldraw's canvas.

## Connect

- streamable-http: `https://tldraw-mcp-app.tldraw.workers.dev/mcp`
- sse: `https://tldraw-mcp-app.tldraw.workers.dev/sse`

## Tools (as reported by the server, not verified)

- `search`: Search the tldraw Editor API spec by writing JavaScript that receives a \`spec\` object and returns a result. The spec contains: spec.members \(all Editor methods/properties with name, kind, signature, description, category\), spec.categories \(category names\), spec.types.shapes \(focused shape type defin
- `exec`: Execute JavaScript code on a tldraw canvas. The code runs in the widget with access to the live \`editor\` instance, helper functions, and normal js. Use the \`search\` tool first to discover available Editor methods and shape types. Each canvas has a unique \`canvasId\`. Omit \`canvasId\` to create a new b
- `\_exec\_callback`: App-only: widget calls this to resolve a pending exec request.
- `\_get\_canvas\_state`: App-only: get the latest checkpoint for a canvas by its canvasId.
- `read\_checkpoint`: App-only: read shapes from a checkpoint by ID.
- `save\_checkpoint`: App-only: save shapes to a checkpoint \(from user edits\). shapesJson and assetsJson must be JSON array strings.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html