Airtable MCP Server
by
Interact with Airtable bases, tables, fields, and records through Claude Desktop or any MCP client, enabling programmatic creation, updating, and searching of Airtable data.
Airtable MCP Server Overview
What is Airtable MCP Server about?
Airtable MCP Server provides a Model Context Protocol interface for managing Airtable resources – bases, tables, fields, and records – directly from Claude Desktop or other MCP‑compatible tools. It streamlines complex table construction by leveraging Claude's agentic capabilities and reduces failure rates common in similar integrations.
How to use Airtable MCP Server?
- Install Node.js (v18+) and verify
node/npmavailability. - Obtain an Airtable API key with the required scopes (data.records:read/write, schema.bases:read/write).
- Configure Claude Desktop to connect to the server using the provided
claude_desktop_config.jsonsnippet. The server runs vianpx @felores/airtable-mcp-serverand expects theAIRTABLE_API_KEYenvironment variable. - Start Claude Desktop – the server appears under Connected MCP Servers.
- Issue natural‑language commands such as
List all basesorCreate a new table with fieldsand receive structured responses.
Key Features
- List, create, and update bases, tables, and fields.
- Full CRUD operations for records, including search and bulk actions.
- Support for all common Airtable field types (text, number, date, single/multi‑select, etc.) and selectable color palettes.
- Staged table‑building workflow that minimizes errors during complex schema creation.
- Ready‑made system prompt and project‑knowledge markdown files to guide Claude agents.
Use Cases
- Rapid prototyping of Airtable schemas directly from conversational AI.
- Automated data migration between Airtable bases by scripting record operations through MCP.
- Dynamic form generation where field definitions are created on‑the‑fly based on user input.
- Integration layer for internal tools that need to read/write Airtable data without writing custom API code.
- Team collaboration where non‑technical members can manage Airtable structures via natural language.
FAQ
Q: Do I need to install the server globally?
A: No. The recommended method uses npx, which fetches and runs the package on demand.
Q: Which environment variable stores the key?
A: AIRTABLE_API_KEY must be set in the MCP server configuration.
Q: Can I run the server locally for development?
A: Yes. Clone the repo, run npm install && npm run build && node build/index.js, then point Claude Desktop to the local node executable.
Q: What Node.js version is required? A: Version 18 or higher.
Q: Is the server open‑source? A: Yes, it is released under the MIT license on GitHub.
Airtable MCP Server's README
Airtable MCP Server
A Model Context Protocol server that provides tools for interacting with Airtable's API. This server enables programmatic management of Airtable bases, tables, fields, and records through Claude Desktop or other MCP clients.
This MCP server features a specialized implementation that allows it to build tables in stages, leveraging Claude's agentic capabilities and minimizing the failure rate typically seen in other MCP servers for Airtable when building complex tables. It also includes system prompt and project knowledge markdown files to provide additional guidance for the LLM when leveraging projects in Claude Desktop.
Requirements: Node.js
- Install Node.js (version 18 or higher) and npm from nodejs.org
- Verify installation:
node --version npm --version
⚠️ Important: Before running, make sure to setup your Airtable API key
Obtaining an Airtable API Key
- Log in to your Airtable account at airtable.com
- Create a personal access token at Airtable's Builder Hub
- In the Personal access token section select these scopes:
- data.records:read
- data.records:write
- schema.bases:read
- schema.bases:write
- Select the workspace or bases you want to give access to the personal access token
- Keep this key secure - you'll need it for configuration
Installation
Method 1: Using npx (Recommended)
-
Navigate to the Claude configuration directory:
- Windows:
C:\Users\NAME\AppData\Roaming\Claude - macOS:
~/Library/Application Support/Claude/
You can also find these directories inside the Claude Desktop app: Claude Desktop > Settings > Developer > Edit Config
- Windows:
-
Create or edit
claude_desktop_config.json:
{
"mcpServers": {
"airtable": {
"command": "npx",
"args": ["@felores/airtable-mcp-server"],
"env": {
"AIRTABLE_API_KEY": "your_api_key_here"
}
}
}
}
Note: For Windows paths, use double backslashes (\) or forward slashes (/).
Method 2: Using mcp-installer:
mcp-installer is a MCP server to install other MCP servers.
- Install mcp-installer
- Install the Airtable MCP server by prompting Claude Desktop:
Install @felores/airtable-mcp-server set the environment variable AIRTABLE_API_KEY to 'your_api_key'
Claude will install the server, modify the configuration file and set the environment variable AIRTABLE_API_KEY to your Airtable API key.
Method 3: Local Development Installation
If you want to contribute or modify the code run this in your terminal:
# Clone the repository
git clone https://github.com/felores/airtable-mcp.git
cd airtable-mcp
# Install dependencies
npm install
# Build the server
npm run build
# Run locally
node build/index.js
Then modify the Claude Desktop configuration file to use the local installation:
{
"mcpServers": {
"airtable": {
"command": "node",
"args": ["path/to/airtable-mcp/build/index.js"],
"env": {
"AIRTABLE_API_KEY": "your_api_key_here"
}
}
}
}
Verifying Installation
- Start Claude Desktop
- The Airtable MCP server should be listed in the "Connected MCP Servers" section
- Test with a simple command:
List all bases
Features
Available Operations
Base Management
list_bases: List all accessible Airtable baseslist_tables: List all tables in a basecreate_table: Create a new table with fieldsupdate_table: Update a table's name or description
Field Management
create_field: Add a new field to a tableupdate_field: Modify an existing field
Record Operations
list_records: Retrieve records from a tablecreate_record: Add a new recordupdate_record: Modify an existing recorddelete_record: Remove a recordsearch_records: Find records matching criteriaget_record: Get a single record by its ID
Field Types
singleLineText: Single line text fieldmultilineText: Multi-line text areaemail: Email address fieldphoneNumber: Phone number fieldnumber: Numeric field with optional precisioncurrency: Money field with currency symboldate: Date field with format optionssingleSelect: Single choice from optionsmultiSelect: Multiple choices from options
Field Colors
Available colors for select fields:
blueBright,redBright,greenBrightyellowBright,purpleBright,pinkBrightgrayBright,cyanBright,orangeBrightblueDark1,greenDark1
Contributing
We welcome contributions to improve the Airtable MCP server! Here's how you can contribute:
-
Fork the Repository
- Visit https://github.com/felores/airtable-mcp
- Click the "Fork" button in the top right
- Clone your fork locally:
git clone https://github.com/your-username/airtable-mcp.git
-
Create a Feature Branch
git checkout -b feature/your-feature-name -
Make Your Changes
- Follow the existing code style
- Add tests if applicable
- Update documentation as needed
-
Commit Your Changes
git add . git commit -m "feat: add your feature description" -
Push to Your Fork
git push origin feature/your-feature-name -
Create a Pull Request
- Go to your fork on GitHub
- Click "New Pull Request"
- Select your feature branch
- Describe your changes in detail
Development Guidelines
- Use TypeScript for new code
- Follow semantic commit messages
- Update documentation for new features
- Add examples for new functionality
- Test your changes thoroughly
Getting Help
- Open an issue for bugs or feature requests
- Join discussions in existing issues
- Ask questions in pull requests
Your contributions help make this tool better for everyone. Whether it's:
- Adding new features
- Fixing bugs
- Improving documentation
- Suggesting enhancements
We appreciate your help in making the Airtable MCP server more powerful and user-friendly!
License
Made with ❤️ by the Airtable MCP community
Airtable MCP Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Airtable MCP Server's Information
- Author
- felores
- Category
- Development Tools
- Language
- JavaScript
- License
- Other
- Version
- v0.3.0
- Stars
- 64
- Updated
- 21 days ago
Configuration
{
"mcpServers": {
"airtable": {
"command": "npx",
"args": [
"-y",
"@felores/airtable-mcp-server"
],
"env": {
"AIRTABLE_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Configure Clients
Similar MCP Servers like Airtable MCP Server
Explore related MCPs that share similar capabilities and solve comparable challenges
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
GitHub MCP Server
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
Daytona
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.