domdomegg/airtable-mcp-server

What it solves

This project provides a bridge between Large Language Models (LLMs) and Airtable databases. It allows AI agents to interact with your data by giving them the ability to read, search, and modify records, as well as manage the structure of your bases, tables, and fields.

How it works

It is implemented as a Model Context Protocol (MCP) server. This means it can be plugged into MCP-compatible clients (like Claude Desktop, Cursor, or VS Code) to expose a set of tools that the LLM can call. The server connects to Airtable via an API key, providing tools for listing bases, describing table schemas, searching for records, and performing CRUD (Create, Read, Update, Delete) operations on records and comments.

Who it’s for

Developers and AI users who want their AI assistants to have direct, read/write access to their Airtable databases for data management or automated workflows.

Highlights

• Full Database Management: Supports creating, updating, and deleting tables and fields, not just records.
• Comprehensive Record Operations: Includes tools for searching records with formulas, retrieving specific records, and managing record comments.
• Flexible Transport: Supports both standard input/output (stdio) for local use and HTTP transport for remote clients.
• Schema Inspection: Allows LLMs to inspect base and table structures to understand how to interact with the data correctly.