AITable MCP Server
Enables interaction with AITable workspaces through comprehensive API access, supporting record and field management, datasheet creation, file uploads, and workspace search across 16 tools with both local and remote deployment options.
README
AITable MCP Server
A Model Context Protocol (MCP) server for AITable with dual transport support:
- stdio - for local use with Claude Desktop
- HTTP (Streamable) - for remote use / deployment
Features
16 Available Tools
Records Management:
get_records- Get records from datasheets (up to 1000 per request, 11 query parameters)create_records- Create new records (up to 10 per request)update_records- Update existing records (up to 10 per request)delete_records- Delete records (up to 10 per request)
Fields Management:
get_fields- Get field metadata from datasheetscreate_field- Create new fields in datasheetsdelete_field- Delete fields from datasheets
Views & Datasheets:
get_views- Get views from datasheetscreate_datasheet- Create new datasheets with custom fields
Attachments:
upload_attachment- Upload files to datasheets
Nodes & Workspace:
get_node_list- Get list of files in workspace (Fusion API v3)search_nodes- Search nodes by type, permissions, and keywords (v2)get_node_detail- Get detailed information about specific nodes
Embed Links:
create_embed_link- Create embeddable links for nodesget_embed_links- List all embed links for a node (up to 30)delete_embed_link- Delete/disable embed links
Important Notes
Default Field Names: When creating datasheets without specifying fields, AITable auto-generates 3 default fields with Chinese names (选项, 标题, 附件). To ensure English field names, always specify fields explicitly when using create_datasheet.
File Upload Requirements:
- Use absolute file paths when uploading attachments (e.g.,
C:/Users/YourName/Documents/file.pdf) - Maximum file size: 1 GB per attachment
- Only one file can be uploaded per API call
- Supported formats: Images, PDFs, documents, and other common file types
Setup
- Install dependencies:
pnpm install
- Configure environment variables:
Copy .env.example to .env:
cp .env.example .env
Then edit .env with your credentials:
# Get your API token from https://aitable.ai workspace settings
AITABLE_API_TOKEN=your_api_token_here
# Get your space ID from your AITable workspace URL (e.g., spcX9P2xUcKst)
SPACE_ID=your_space_id_here
- Build the project:
pnpm build
Usage
Option 1: stdio Server (for Claude Desktop)
Configure Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):
Production (recommended):
{
"mcpServers": {
"aitable": {
"command": "node",
"args": ["C:/Users/YourName/code/aitable-mcp/dist/stdio-server.js"],
"env": {
"AITABLE_API_TOKEN": "your_token_here",
"SPACE_ID": "your_space_id_here"
}
}
}
}
Development mode with tsx:
{
"mcpServers": {
"aitable": {
"command": "npx",
"args": ["-y", "tsx", "C:/Users/YourName/code/aitable-mcp/src/stdio-server.ts"],
"env": {
"AITABLE_API_TOKEN": "your_token_here",
"SPACE_ID": "your_space_id_here"
}
}
}
}
After configuration:
- Save the config file
- Restart Claude Desktop
- Claude will now have access to all 16 AITable tools
Option 2: HTTP Server (for remote access)
Local Development:
pnpm dev:http
The server will run at http://localhost:3000/mcp.
Test with the client:
pnpm client
Option 3: Deploy to Vercel
- Install Vercel CLI:
npm i -g vercel
- Deploy:
vercel --prod
-
Set environment variables in Vercel Dashboard:
- Go to your project settings
- Add
AITABLE_API_TOKEN - Add
SPACE_ID
-
Your MCP server will be available at:
https://your-project.vercel.app/api/mcp
Health check endpoint:
https://your-project.vercel.app/api/health
- Use as Custom Connector:
- The Vercel URL can be added as a custom MCP connector in ChatGPT and Claude Desktop
- Use your deployment URL:
https://your-project.vercel.app/api/mcp
Development
Build TypeScript:
pnpm build
Run stdio server (development):
pnpm dev:stdio
Run HTTP server (development):
pnpm dev:http
Test with client:
pnpm client
Project Structure
aitable-mcp/
├── src/
│ ├── types.ts # AITable API type definitions
│ ├── aitable-tools.ts # Shared tool implementations (16 tools)
│ ├── stdio-server.ts # stdio transport server (Claude Desktop)
│ ├── http-server.ts # HTTP transport server (local/remote)
│ └── client.ts # Test client
├── api/
│ └── mcp.ts # Vercel serverless function
├── dist/ # Compiled JavaScript (not committed)
├── .env # Your credentials (not committed)
├── .env.example # Example environment file
├── .gitignore # Git ignore rules
├── vercel.json # Vercel deployment config
└── package.json
API Rate Limits
AITable has different rate limits based on your plan:
- Free: 2 QPS
- Plus: 5 QPS
- Pro: 10 QPS
- Enterprise: 20 QPS
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。