by hamchowderr
AITable MCP Server: full AITable API access and workspace API, datasheet API, and record management API—file uploads and
Connects to AITable workspaces for managing records, fields, and datasheets through comprehensive API access. Supports file uploads and workspace search across multiple tools.
AITable MCP Server is a community-built MCP server published by hamchowderr that provides AI assistants with tools and capabilities via the Model Context Protocol. AITable MCP Server: full AITable API access and workspace API, datasheet API, and record management API—file uploads and It is categorized under databases, developer tools.
You can install AITable MCP Server in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
AITable MCP Server is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Enable Claude to query your database directly using natural language
Example
Ask 'Show me top 10 customers by revenue this month' and get SQL results instantly
Eliminate manual SQL writing for ad-hoc queries, get insights 10x faster
Generate complex reports and analytics without leaving conversation
Example
Analyze sales trends, cohort retention, user behavior patterns conversationally
Democratize data access—non-technical team members can query databases
Understand database structure, relationships, and data models
Example
'Explain the user_orders table schema and its relationships'
Onboard engineers faster, explore unfamiliar databases efficiently
Share your MCP server with the developer community
According to our notes, AITable MCP Server benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
We wired AITable MCP Server into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
AITable MCP Server reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Useful MCP listing: AITable MCP Server is the kind of server we cite when onboarding engineers to host + tool permissions.
AITable MCP Server reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
AITable MCP Server is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: AITable MCP Server is the kind of server we cite when onboarding engineers to host + tool permissions.
I recommend AITable MCP Server for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
According to our notes, AITable MCP Server benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
AITable MCP Server is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
showing 1-10 of 34

Model Context Protocol (MCP) server for integrating with AITable platform.
⚠️ Important: AITable has been discontinued. If you're looking to migrate to Bika (the successor platform), check out the Bika MCP Server.
AITable LTD Holders: Claim your free Bika account by filling out this migration form (available only for AITable LTD users).
This MCP server provides integration with AITable's API, enabling AI assistants to:
Once published, you can install directly via npx:
# No installation needed! Run directly with npx
npx aitable-mcp
# Clone the repository
git clone https://github.com/hamchowderr/aitable-mcp.git
cd aitable-mcp
# Install dependencies
npm install
# Build the project
npm run build
The server requires the following environment variables:
| Variable | Required | Description |
|---|---|---|
AITABLE_API_TOKEN | Yes | Your AITable API access token |
SPACE_ID | Yes | Your AITable space ID |
Option 1: Environment variables
# Windows
set AITABLE_API_TOKEN=your-api-token-here
set SPACE_ID=your-space-id
# macOS/Linux
export AITABLE_API_TOKEN="your-api-token-here"
export SPACE_ID="your-space-id"
Option 2: Create a .env file
Create a .env file in the project root:
AITABLE_API_TOKEN=your-api-token-here
SPACE_ID=your-space-id
The recommended way to use this MCP server is with Claude Desktop using stdio transport.
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonAdd to your Claude Desktop configuration:
{
"mcpServers": {
"aitable": {
"command": "npx",
"args": ["-y", "aitable-mcp"],
"env": {
"AITABLE_API_TOKEN": "your-token-here",
"SPACE_ID": "your-space-id"
}
}
}
}
For development or local installations:
{
"mcpServers": {
"aitable": {
"command": "node",
"args": ["C:\absolute\path\ o\aitable-mcp\dist\stdio-server.js"],
"env": {
"AITABLE_API_TOKEN": "your-token-here",
"SPACE_ID": "your-space-id"
}
}
}
}
Important: Restart Claude Desktop after updating the configuration.
Test your server locally with the official MCP Inspector:
# Run the inspector
npm run inspector
# Or run directly
npx @modelcontextprotocol/inspector dist/stdio-server.js
This will:
http://localhost:6274Run the server directly for stdio transport:
# Build and start
npm run build
npm start
# Development mode with watch
npm run dev
Deploy as a custom connector for HTTP-based MCP access.
Initial Deployment:
# Install Vercel CLI if needed
npm install -g vercel
# Deploy to Vercel
npx vercel@latest
Production Deployment:
npx vercel@latest --prod
Set Environment Variables:
In your Vercel project settings (Settings → Environment Variables), add:
AITABLE_API_TOKEN - Your AITable API token (required for authenticating with AITable)SPACE_ID - Your AITable space ID (required)Important: Ensure both variables are enabled for all environments (Production, Preview, and Development). If Preview is unchecked, preview deployment URLs will fail with "Connection refused".
Disable Deployment Protection (Required for MCP):
In your Vercel project settings (Settings → Deployment Protection):
Configure as Custom Connector in Claude Desktop:
IMPORTANT: Custom connectors must be configured via the Claude Desktop UI, NOT via claude_desktop_config.json.
To add the custom connector:
https://your-project.vercel.app/mcpNote: Make sure to include /mcp at the end of the URL!
Test the Deployment:
# Test with the test script
node scripts/test-streamable-http-client.mjs https://your-project.vercel.app
Stdio vs HTTP Transport:
Which to use?
This MCP server uses different authentication strategies depending on the transport:
Stdio Transport (Recommended for Personal Use)
claude_desktop_config.jsonHTTP Transport (Custom Connector)
IMPORTANT:
AITABLE_API_TOKEN secret - it grants full access to your AITable dataThis MCP server supports dual transport following official MCP patterns:
npx or node dist/stdio-server.jsmcp-handler library for HTTP transportBoth transports share the same core business logic while providing different communication mechanisms.
aitable-mcp/
├── src/
│ ├── stdio-server.ts # Stdio entry point
│ ├── http-server.ts # Local HTTP server for testing
│ ├── aitable-tools.ts # MCP tool implementations
│ ├── formula-resource.ts # Formula documentation provider
│ ├── types.ts # TypeScript type definitions
│ └── *.md # Formula documentation files
├── api/
│ └── server.ts # HTTP entry point (Vercel)
├── public/
│ └── index.html # Landing page
├── scripts/
│ ├── test-client.mjs # SSE transport tester
│ └── test-streamable-http-client.mjs # HTTP transport tester
├── dist/ # Compiled output
├── package.json
├── tsconfig.json
├── vercel.json # Vercel configuration
└── README.md
The MCP server provides comprehensive AITable integration tools:
get_records - Query records with filtering, sorting, and paginationcreate_records - Create new records (max 10 per request)update_records - Update existing records (max 10 per request)delete_records - Delete records (max 10 per request)get_fields - Get field metadata from datasheetscreate_field - Create new fields in datasheetsdelete_field - Delete fields from datasheetsget_views - Get views from datasheetscreate_datasheet - Create new datasheets with custom fieldsupload_attachment - Upload files to datasheetsget_node_list - Get list of files in workspacesearch_nodes - Search nodes by type, permissions, and keywordsget_node_detail - Get detailed information about specific nodescreate_embed_link - Create embeddable links for nodesget_embed_links - List all embed links for a nodedelete_embed_link - Delete/disable embed linksFormula reference documentation:
formula_overview - Quick reference guide to AITable formulasRun data quality queries to catch anomalies and inconsistencies
Example
Find duplicate records, missing values, orphaned foreign keys automatically
Maintain data integrity with less manual SQL work
Prerequisites
Time Estimate
15-30 minutes including configuration and testing
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
MCP server acts as bridge between Claude and database, translating natural language to SQL queries and returning results in structured format.
Protocols
Compatibility
✓ Use when
Use for ad-hoc data queries, exploratory analysis, report generation, schema exploration, and democratizing data access. Best for read-heavy analytics workloads.
✗ Avoid when
Avoid for production write operations, mission-critical transactions, real-time OLTP workloads, or when database contains sensitive PII without proper access controls. Use read replicas, not primary.