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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases