tldraw MCP

tldraw MCP

Enables AI agents to read, write, and search local tldraw (.tldr) files, providing a persistent visual scratchpad for diagramming and note organization. It supports full CRUD operations on canvas shapes and metadata management for local canvas files.

Category
访问服务器

README

@talhaorak/tldraw-mcp

npm version License: MIT

MCP (Model Context Protocol) server for managing local tldraw canvas files (.tldr).

What Makes This Different?

Existing tldraw MCP servers let AI draw on an in-memory canvas. This project is different — it reads, writes, and searches local .tldr files on disk, making tldraw a persistent visual scratchpad that AI agents can programmatically update.

Features

  • 📖 Read — Load and parse .tldr files
  • ✍️ Write — Create and update canvas files with validation
  • 📋 List — Enumerate all .tldr files with metadata
  • 🔍 Search — Full-text search across all canvases
  • 🔷 Shape CRUD — Add, update, delete shapes programmatically

Installation

npm (recommended)

npx @talhaorak/tldraw-mcp

From source

git clone https://github.com/talhaorak/tldraw-mcp.git
cd tldraw-mcp
bun install
bun run start

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "tldraw": {
      "command": "npx",
      "args": ["@talhaorak/tldraw-mcp"],
      "env": {
        "TLDRAW_DIR": "/path/to/your/tldraw/files"
      }
    }
  }
}

OpenClaw

Add to your OpenClaw config:

mcp:
  servers:
    tldraw:
      command: npx
      args: ["@talhaorak/tldraw-mcp"]
      env:
        TLDRAW_DIR: /path/to/your/tldraw/files

Or install as a skill:

curl -fsS https://raw.githubusercontent.com/talhaorak/tldraw-mcp/main/SKILLS.md | bash

Environment Variables

Variable Default Description
TLDRAW_DIR ~/.tldraw Base directory for .tldr files

Tools

tldraw_read

Read a .tldr file and return its parsed content.

tldraw_read({ path: "notes.tldr" })

tldraw_write

Write or update a .tldr file (validates format).

tldraw_write({ 
  path: "notes.tldr",
  content: { /* tldraw file object */ }
})

tldraw_create

Create a new empty tldraw canvas.

tldraw_create({ path: "new-canvas.tldr", name: "My Canvas" })

tldraw_list

List all .tldr files with page/shape counts.

tldraw_list({ recursive: true })

tldraw_search

Search text content across all canvases.

tldraw_search({ query: "TODO", searchIn: "text" })

tldraw_get_shapes

Get all shapes from a file, optionally filtered by page.

tldraw_get_shapes({ path: "notes.tldr", pageId: "page:abc123" })

tldraw_add_shape

Add a new shape to a canvas.

tldraw_add_shape({
  path: "notes.tldr",
  shape: {
    type: "geo",
    x: 100,
    y: 100,
    props: {
      w: 200,
      h: 100,
      geo: "rectangle",
      color: "blue",
      fill: "semi"
    }
  }
})

tldraw_update_shape

Update properties of an existing shape.

tldraw_update_shape({
  path: "notes.tldr",
  shapeId: "shape:abc123",
  updates: { x: 200, props: { color: "red" } }
})

tldraw_delete_shape

Delete a shape from a canvas.

tldraw_delete_shape({
  path: "notes.tldr",
  shapeId: "shape:abc123"
})

Use Cases

  • Visual scratchpad for AI agents — AI updates a canvas you can view in tldraw
  • Diagram generation — Create flowcharts, architecture diagrams programmatically
  • Note organization — Search and organize visual notes across multiple canvases
  • Integration with tldraw desktop/VS Code — Files sync automatically

tldraw File Format

This server works with tldraw v2 format:

{
  "tldrawFileFormatVersion": 1,
  "schema": {
    "schemaVersion": 2,
    "sequences": { ... }
  },
  "records": [
    { "id": "document:document", "typeName": "document", ... },
    { "id": "page:xxx", "typeName": "page", ... },
    { "id": "shape:xxx", "typeName": "shape", "type": "geo", ... }
  ]
}

Development

# Install dependencies
bun install

# Run in development mode
bun run dev

# Type check
bun run typecheck

# Build for distribution
bun run build

# Run tests
bun test

Publishing

./scripts/publish.sh          # Auto-increment patch (0.1.0 → 0.1.1)
./scripts/publish.sh 0.2.0    # Use specific version
./scripts/publish.sh minor    # Bump minor (0.1.1 → 0.2.0)
./scripts/publish.sh major    # Bump major (0.2.0 → 1.0.0)

The script updates package.json, commits, tags, and pushes. GitHub Actions handles npm publish automatically via Trusted Publishers.

Security

  • Path traversal prevention — Relative paths can't escape TLDRAW_DIR
  • Format validation — All writes are validated against tldraw schema
  • No network access — Purely local file operations

License

MIT © Talha Orak

Related

  • tldraw — The infinite canvas
  • MCP — Model Context Protocol
  • OpenClaw — AI agent framework

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选