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.
README
@talhaorak/tldraw-mcp
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
.tldrfiles - ✍️ Write — Create and update canvas files with validation
- 📋 List — Enumerate all
.tldrfiles 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
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。