Skip to main content
Glama

Airtable MCP

by mufonix

Airtable MCP

Airtable smithery badge

Connect your AI tools directly to Airtable. Query, create, update, and delete records using natural language. Features include base management, table operations, schema manipulation, record filtering, and data migration—all through a standardized MCP interface compatible with Cursor, Claude Code, Cline, Zed, and other Claude-powered editors.

This application is a powerful Airtable integration tool that enables AI-powered applications via Anthropic's Model Context Protocol (MCP) to access and manipulate Airtable data directly from your IDE.

Features

  • Base Management: List and select Airtable bases

  • Table Operations: Browse tables, fields, and records

  • Data Access: Read, create, update, and delete records

  • Schema Management: Export, compare, and update schemas

  • Command-line Configuration: Use API tokens directly through command-line parameters

  • NPX Compatible: Easy installation with a single command

  • Smithery Integration: One-click installation via Smithery

Architecture

There are two core components used to access and manipulate Airtable data:

  1. Airtable MCP Server: A Python server that provides standardized tools for AI clients to interact with Airtable.

  2. MCP Client: Any client that supports the Model Context Protocol (Cursor, Claude Desktop, Cline, Zed, etc.).

┌─────────────┐ ┌──────────────┐ ┌───────────────┐ │ MCP Client │ ──► │ Airtable │ ──► │ Airtable │ │ (e.g. │ ◄── │ MCP Server │ ◄── │ API │ │ Cursor) │ │ │ │ │ └─────────────┘ └──────────────┘ └───────────────┘

Model Context Protocol (MCP) is a capability supported by Anthropic AI models that allows you to create custom tools for any compatible client. MCP clients like Claude Desktop, Cursor, Cline, or Zed can run an MCP server which "teaches" these clients about new tools they can use.

Installation

Prerequisites

  • Node.js 14+

  • Python 3.10+ (automatically detected)

  • Airtable API token

  • A compatible MCP client (Cursor, Claude Desktop, etc.)

Smithery Installation (Recommended)

The easiest way to install:

  1. Visit Smithery

  2. Search for "@rashidazarang/airtable-mcp"

  3. Click "Install" and follow the prompts

Quick Setup with NPX (Alternative)

Another fast way to get started:

# Install globally npm install -g airtable-mcp # Or run directly with npx npx airtable-mcp --token "your_airtable_token" --base "your_base_id"

Configure Your MCP Client

For Cursor, update your ~/.cursor/mcp.json file:

{ "mcpServers": { "airtable-tools": { "command": "npx", "args": [ "airtable-mcp", "--token", "your_airtable_token", "--base", "your_base_id" ] } } }

Restart your MCP client to load the new tools.

Manual Installation (Advanced)

If you prefer to clone the repository and install manually:

  1. Clone this repository:

    git clone https://github.com/rashidazarang/airtable-mcp.git cd airtable-mcp
  2. Install dependencies:

    pip install -r requirements.txt
  3. Run the server:

    python airtable_mcp/src/server.py --token "your_airtable_token" --base "your_base_id"

Usage

Once installed and configured, you can use natural language to interact with your Airtable data:

  • "Show me all the bases I have access to"

  • "List the tables in my current base"

  • "Show me the structure of the Customers table"

  • "Get the first 10 records from the Orders table"

  • "Create a new record in the Products table"

  • "Update record XYZ in the Inventory table"

  • "Export the schema of my current base"

Available Tools

Tool Name

Description

list_bases

List all accessible Airtable bases

list_tables

List all tables in the specified or default base

list_records

List records from a table with optional filtering

get_record

Get a specific record from a table

create_records

Create records in a table from JSON string

update_records

Update records in a table from JSON string

delete_records

Delete records from a table by IDs

export_records

Export records from a table as JSON string

import_records

Import records to a table from JSON string

create_tables

Create tables from a JSON schema

update_schema

Update existing tables to match a JSON schema

set_base_id

Set the current Airtable base ID

inspect_table

Get detailed information about a table's structure and fields

export_schema

Export the schema of the current base in JSON or CSV format

compare_schemas

Compare the provided schema with the current base schema

generate_field_mapping

Generate a field mapping between two tables

migrate_data

Migrate data from one table to another using the specified field mapping

PM2 Configuration

For production use, you can use PM2 to manage the Airtable MCP server:

// ecosystem.config.js module.exports = { apps: [ { name: 'airtable-mcp', script: 'npx', args: [ 'airtable-mcp', '--token', 'your_airtable_token', '--base', 'your_base_id' ], interpreter: '/usr/local/bin/node', env: { PATH: process.env.PATH, }, }, ], };

Start with:

pm2 start ecosystem.config.js

Compatibility

  • Works with any MCP-compatible client

  • Primarily designed for Cursor IDE integration

  • Supports other AI editors and MCP clients

Detailed Documentation

For detailed installation instructions, troubleshooting, and advanced configurations, see INSTALLATION.md.

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

-
security - not tested
A
license - permissive license
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

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.

  1. Features
    1. Architecture
      1. Installation
        1. Prerequisites
        2. Smithery Installation (Recommended)
        3. Quick Setup with NPX (Alternative)
        4. Configure Your MCP Client
        5. Manual Installation (Advanced)
      2. Usage
        1. Available Tools
          1. PM2 Configuration
            1. Compatibility
              1. Detailed Documentation
                1. License
                  1. Contributing

                    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 -
                      870
                      MIT License
                      • Linux
                      • Apple
                    • -
                      security
                      A
                      license
                      -
                      quality
                      Provides code manipulation, execution, and version control capabilities. It allows AI assistants to read, write, and execute code while maintaining a history of changes.
                      Last updated -
                      9
                      MIT License
                    • -
                      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 -
                      67
                      • Apple
                    • -
                      security
                      A
                      license
                      -
                      quality
                      Connects AI tools directly to Airtable, allowing users to query, create, update, and delete records using natural language.
                      Last updated -
                      75
                      37
                      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/mufonix/airtable-mcp'

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