Airtable MCP Server
The Airtable MCP Server lets your AI read and write your Airtable base directly — query records, create rows, update fields — all in natural language.
For example, "log these customer feedback notes into my Airtable CRM table and set priorities" — the AI uses this server to write them in bulk.
What it does for you
Lets your AI work with Airtable — query records, add data, update tables, managing your bases through chat.
Capabilities
- Query / filter records
- Create / update records
Once installed, try asking your AI
Say this directly in Claude / Cursor or any client with this server connected
- ›“Add a record to the customers table: Acme, status follow-up”
Install / Connect
claude mcp add airtable-mcp-server -- npx -y airtable-mcp-serverFollow the official README; env and args vary per server.
Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Why use it
Good for: teams using Airtable as a lightweight database/CRM who want AI to cut manual data entry and lookups.
Actively maintained; its health and maintenance data on this site is shown below.
Similar / alternative servers
dbt-mcp
A MCP (Model Context Protocol) server for interacting with dbt.
ai.dinglebear/soma
Soma
linkedin-mcp-server
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent
jupyter-mcp-server
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
Frequently Asked Questions
What permissions does it need?
An Airtable personal access token, scoped to the bases you want it to access.
Could it change my data by mistake?
It has write access, so give clear instructions; rehearse with a test base before pointing it at important data.