airtable-mcp-server

Name: airtable-mcp-server
Author: domdomegg

@domdomegg

Repository Homepage

About airtable-mcp-server

🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases

#airtable #model-context-protocol #mcp-server

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "airtable-mcp-server": {
      "command": "npx",
      "args": [
        "airtable-mcp-server"
      ],
      "env": {
        "MCP_TRANSPORT": "http",
        "PORT": "3000"
      }
    }
  }
}

Tools

Lists records from a specified Airtable table

Search for records containing specific text

Lists all accessible Airtable bases

Lists all tables in a specific base

Gets detailed information about a specific table

Gets a specific record by ID

Creates a new record in a table

Updates one or more records in a table

Deletes one or more records from a table

Creates a new table in a base

Updates a table's name or description

Creates a new field in a table

Updates a field's name or description

Creates a comment on a record

Lists comments on a record

Overview

What is airtable-mcp-server?

A Model Context Protocol server that provides read and write access to Airtable databases. It enables LLMs to inspect database schemas, then read and write records. It is intended for use with MCP-compatible clients like Claude Code, Claude Desktop, Cursor, Cline, and VS Code.

How to use airtable-mcp-server?

Install via the generated config link or by running npx airtable-mcp-server. You must set the environment variable AIRTABLE_API_KEY to an Airtable personal access token with the appropriate scopes (at minimum schema.bases:read and data.records:read). The server exposes multiple tools for interacting with Airtable bases, tables, records, fields, and comments.

Key features of airtable-mcp-server

List, search, create, update, and delete records
List and describe bases, tables, and fields
Read and write comments on records
Create and update tables and fields
Filter records using Airtable formulas
Run as HTTP server for remote clients

Use cases of airtable-mcp-server

Allow an LLM to query and update an Airtable CRM
Automate data entry by creating records from natural language
Let AI assistants explore and modify database schemas
Enable conversational retrieval of Airtable records with filters
Support threaded commenting on records via AI

FAQ from airtable-mcp-server

What authentication is needed?

You need an Airtable personal access token (looks like pat123.abc123) with scopes schema.bases:read and data.records:read as a minimum. For write operations add schema.bases:write, data.records:write, data.recordComments:read, and data.recordComments:write.

Can the server be used remotely?

Yes, by setting MCP_TRANSPORT=http and optionally PORT=3000, the server runs in HTTP mode at http://localhost:3000/mcp. Note that HTTP transport has no built‑in authentication — only use behind a reverse proxy or in a secured environment.

What tools does airtable-mcp-server provide?

It provides tools for listing/searching records, retrieving a single record, creating/updating/deleting records, listing bases and tables, describing a table, creating/updating tables and fields, and creating/listening comments. Full parameter details are in the README.

How do I install airtable-mcp-server?

Use the install-mcp guide or run npx airtable-mcp-server. The generated config handles environment variables and client setup for supported MCP clients.

Can I contribute to the project?

Yes, pull requests are welcome. Clone the repository, install dependencies with npm install, run tests with npm run test, and build with npm run build. Use npm run build:watch for automatic rebuilding during development.

Comments

More Other MCP servers

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K