Skip to main content
Glama

Airtable MCP Server

by cipher416

Airtable MCP

An MCP (Model Context Protocol) server that provides tools for interacting with Airtable bases and schemas.

Overview

This project implements an xMCP application that allows AI assistants to interact with Airtable.

Features

  • šŸ—ƒļø List all accessible Airtable bases

  • šŸ“‹ Retrieve detailed schema information for any base

  • šŸ”’ Secure authentication using Airtable API keys

  • šŸš€ Built with TypeScript and xMCP framework

  • šŸ”§ HTTP server support for easy integration

Prerequisites

  • Node.js >= 20.0.0

  • Airtable API key

  • Access to Airtable bases

Installation

  1. Clone the repository:

git clone <repository-url> cd airtable-mcp
  1. Install dependencies:

npm install
  1. Set up environment variables: Create a .env file in the root directory with:

AIRTABLE_API_KEY=your_airtable_api_key_here AIRTABLE_API_URL=https://api.airtable.com

Getting Started

Run the development server:

npm run dev

Build for production:

npm run build npm start

Available Tools

listBases

  • Description: List all Airtable bases owned by the user

  • Parameters: None

  • Returns: JSON array of bases with their metadata

getBaseSchema

  • Description: Get the schema of a specific Airtable base

  • Parameters:

    • baseId (string): The ID of the Airtable base

  • Returns: JSON object containing the base's table schemas

Scripts

  • npm run dev - Start development server with hot reload

  • npm run build - Build the project for production

  • npm start - Start the production HTTP server

  • npm run lint - Run TypeScript type checking

Project Structure

airtable-mcp/ ā”œā”€ā”€ src/ │ └── tools/ ā”œā”€ā”€ package.json ā”œā”€ā”€ xmcp.config.ts # xMCP configuration └── tsconfig.json # TypeScript configuration

This project uses the structured approach where tools are automatically discovered from the src/tools directory. Each tool is defined in its own file with the following structure:

import { type ToolMetadata, InferSchema } from "xmcp"; import { z } from "zod"; // Define the schema for tool parameters (optional) export const schema = { baseId: z.string(), }; // Define tool metadata export const metadata: ToolMetadata = { name: "getBaseSchema", description: "List the schema of the base owned by the user", annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, }, }; // Tool implementation export default async function getBaseSchema(args: InferSchema<typeof schema>) { // Implementation here }

Dependencies

  • airtable: Official Airtable JavaScript client

  • xmcp: xMCP framework for building MCP servers

  • zod: Runtime type validation

Learn More

-
security - not tested
F
license - not found
-
quality - not tested

Related MCP Servers

  • A
    security
    A
    license
    A
    quality
    Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.
    Last updated -
    983
    MIT License
    • Linux
    • Apple
  • -
    security
    F
    license
    -
    quality
    Enables AI assistants to interact with Metabase databases and dashboards, allowing users to list and execute queries, access data visualizations, and interact with database resources through natural language.
    Last updated -
    83
    • Apple
  • -
    security
    -
    license
    -
    quality
    Enables AI-powered applications to access and manipulate Airtable data directly from your IDE, supporting operations like querying, creating, updating, and deleting records through natural language commands.
  • -
    security
    A
    license
    -
    quality
    Connects AI tools directly to Airtable, allowing users to query, create, update, and delete records using natural language.
    Last updated -
    49
    45
    MIT License
    • Apple

View all related MCP servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cipher416/airtable-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server