Excalidraw MCP App Server
Enables users to create and interact with hand-drawn Excalidraw diagrams featuring smooth viewport camera control and interactive fullscreen editing. It uses the MCP Apps extension to render collaborative virtual whiteboards directly within supported AI chat interfaces.
README
Excalidraw MCP App Server
MCP server that streams hand-drawn Excalidraw diagrams with smooth viewport camera control and interactive fullscreen editing.

Install
Works with any client that supports MCP Apps — Claude, ChatGPT, VS Code, Goose, and others. If something doesn't work, please open an issue.
Remote (recommended)
https://excalidraw-mcp-app.vercel.app/mcp
Add as a remote MCP server in your client. For example, in claude.ai: Settings → Connectors → Add custom connector → paste the URL above.
Local
Option A: Download Extension
- Download
excalidraw-mcp-app.mcpbfrom Releases - Double-click to install in Claude Desktop
Option B: Build from Source
git clone https://github.com/antonpk1/excalidraw-mcp-app.git
cd excalidraw-mcp-app
npm install && npm run build
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"excalidraw": {
"command": "node",
"args": ["/path/to/excalidraw-mcp-app/dist/index.js", "--stdio"]
}
}
}
Restart Claude Desktop.
Usage
Example prompts:
- "Draw a cute cat using excalidraw"
- "Draw an architecture diagram showing a user connecting to an API server which talks to a database"
What are MCP Apps and how can I build one?
Text responses can only go so far. Sometimes users need to interact with data, not just read about it. MCP Apps is an official Model Context Protocol extension that lets servers return interactive HTML interfaces (data visualizations, forms, dashboards) that render directly in the chat.
- Getting started for humans: documentation
- Getting started for AIs: skill
Contributing
PRs welcome! See Local above for build instructions.
Deploy your own instance
You can deploy your own copy to Vercel in a few clicks:
- Fork this repo
- Go to vercel.com/new and import your fork
- No environment variables needed — just deploy
- Your server will be at
https://your-project.vercel.app/mcp
Release checklist
<details> <summary>For maintainers</summary>
# 1. Bump version in manifest.json and package.json
# 2. Build and pack
npm run build && mcpb pack .
# 3. Create GitHub release
gh release create v0.3.0 excalidraw-mcp-app.mcpb --title "v0.3.0" --notes "What changed"
# 4. Deploy to Vercel
vercel --prod
</details>
Credits
Built with Excalidraw — a virtual whiteboard for sketching hand-drawn like diagrams.
License
MIT
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。