Airtable MCP Server
Advanced AI-powered server enabling enterprise-grade automation and analytics for Airtable through MCP.
Key Features
Use Cases
README
Airtable MCP Server
๐ค Revolutionary AI Agent v3.2.5 - Advanced AI-powered Airtable MCP server with fixed TypeScript architecture, world-class project organization, comprehensive intelligence capabilities, predictive analytics, and enterprise automation features.
๐ Latest: v3.2.5 - Optional Base ID & Enhanced Multi-Base Support
Major Improvements with full backward compatibility:
- ๐ Optional Base ID - Start without specifying a base, discover them using
list_basestool - ๐ Enhanced Base Discovery - New
list_basestool fully implemented in TypeScript - ๐ฏ Dynamic Base Selection - Specify base IDs per tool call, no startup requirement
- โ Fixed Issue #9 - Resolved "base required at startup" limitation
- ๐ง Improved Governance - Smart base allowlist handling for multi-base workflows
- ๐ฆ Full STDIO Support - Confirmed compatibility with Claude Desktop/Code
๐ Previous: v3.2.4 - XSS Security Fix & Complete Protection
Major Improvements with full backward compatibility:
- ๐ง TypeScript Architecture Fixed - Resolved compilation issues, proper separation of types and runtime code
- ๐ World-Class Organization - Restructured project with src/typescript, src/javascript, src/python
- ๐ Security Fix Complete - Fully resolved command injection vulnerability with comprehensive validation
- ๐ท TypeScript Implementation - Complete type-safe server with strict validation
- ๐ Comprehensive Type Definitions - All 33 tools and 10 AI prompts fully typed
- ๐ก๏ธ Compile-Time Safety - Catch errors before runtime with advanced type checking
- ๐ฏ Developer Experience - IntelliSense, auto-completion, and refactoring support
- ๐ Dual Distribution - Use with JavaScript or TypeScript, your choice
๐ค AI Intelligence Suite
Complete AI-Powered Intelligence with enterprise capabilities:
- ๐ค 10 AI Prompt Templates - Advanced analytics, predictions, and automation
- ๐ฎ Predictive Analytics - Forecasting and trend analysis with confidence intervals
- ๐ฃ๏ธ Natural Language Processing - Query your data using human language
- ๐ Business Intelligence - Automated insights and recommendations
- ๐๏ธ Smart Schema Design - AI-optimized database architecture
- โก Workflow Automation - Intelligent process optimization
- ๐ Data Quality Auditing - Comprehensive quality assessment and fixes
- ๐ Statistical Analysis - Advanced analytics with significance testing
โจ Features
- ๐ Natural Language Queries - Ask questions about your data in plain English
- ๐ Full CRUD Operations - Create, read, update, and delete records
- ๐ช Webhook Management - Create and manage webhooks for real-time notifications
- ๐๏ธ Advanced Schema Management - Create tables, fields, and manage base structure
- ๐ Base Discovery - Explore all accessible bases and their schemas
- ๐ง Field Management - Add, modify, and remove fields programmatically
- ๐ Secure Authentication - Uses environment variables for credentials
- ๐ Easy Setup - Multiple installation options available
- โก Fast & Reliable - Built with Node.js for optimal performance
- ๐ฏ 33 Powerful Tools - Complete Airtable API coverage with batch operations
- ๐ Attachment Management - Upload files via URLs to attachment fields
- โก Batch Operations - Create, update, delete up to 10 records at once
- ๐ฅ Collaboration Tools - Manage base collaborators and shared views
- ๐ค AI Integration - Prompts and sampling for intelligent data operations
- ๐ Enterprise Security - OAuth2, rate limiting, comprehensive validation
๐ Prerequisites
- Node.js 14+ installed on your system
- An Airtable account with a Personal Access Token
- Your Airtable Base ID
๐ Quick Start
Step 1: Get Your Airtable Credentials
-
Personal Access Token: Visit Airtable Account โ Create a token with the following scopes:
data.records:read- Read records from tablesdata.records:write- Create, update, delete recordsschema.bases:read- View table schemasschema.bases:write- New in v1.5.0 - Create/modify tables and fieldswebhook:manage- (Optional) For webhook features
-
Base ID: Open your Airtable base and copy the ID from the URL:
https://airtable.com/[BASE_ID]/...
Step 2: Installation
Choose one of these installation methods:
๐ท TypeScript Users (Recommended for Development)
# Install with TypeScript support
npm install -g @rashidazarang/airtable-mcp
# For development with types
npm install --save-dev typescript @types/node
๐ฆ JavaScript Users (Production Ready)
Option A: Install via NPM (Recommended)
npm install -g @rashidazarang/airtable-mcp
Option B: Clone from GitHub
git clone https://github.com/rashidazarang/airtable-mcp.git
cd airtable-mcp
npm install
Step 3: Set Up Environment Variables
Create a .env file in your project directory:
AIRTABLE_TOKEN=your_personal_access_token_here
AIRTABLE_BASE_ID=your_base_id_here # OPTIONAL - can be discovered using list_bases tool
New in v3.2.5: The AIRTABLE_BASE_ID is now optional! You can:
- Start without a base ID and use the
list_basestool to discover your accessible bases - Specify base IDs dynamically in each tool call
- Set a default base for convenience (recommended)
Security Note: Never commit .env files to version control!
Step 4: Configure Your MCP Client
๐ท TypeScript Configuration (Enhanced Developer Experience)
Add to your Claude Desktop configuration file with TypeScript binary:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"airtable-typescript": {
"command": "npx",
"args": ["@rashidazarang/airtable-mcp"],
"env": {
"AIRTABLE_TOKEN": "YOUR_AIRTABLE_TOKEN",
"AIRTABLE_BASE_ID": "YOUR_BASE_ID",
"NODE_ENV": "production",
"LOG_LEVEL": "INFO"
}
}
}
}
Note: AIRTABLE_BASE_ID is optional. Omit it to discover bases using list_bases tool.
๐ฆ JavaScript Configuration (Standard)
Add to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"airtable": {
"command": "npx",
"args": ["@rashidazarang/airtable-mcp"],
"env": {
"AIRTABLE_TOKEN": "YOUR_AIRTABLE_TOKEN",
"AIRTABLE_BASE_ID": "YOUR_BASE_ID"
}
}
}
}
Note: AIRTABLE_BASE_ID is optional. Omit it to discover bases using list_bases tool.
Configuration Without Base ID (New!)
Start without specifying a base and discover them dynamically:
{
"mcpServers": {
"airtable": {
"command": "npx",
"args": ["@rashidazarang/airtable-mcp"],
"env": {
"AIRTABLE_TOKEN": "YOUR_AIRTABLE_TOKEN"
}
}
}
}
Then use the list_bases tool to discover your accessible bases!
Step 5: Restart Your MCP Client
After configuration, restart Claude Desktop or your MCP client to load the Airtable server.
๐ฏ Usage Examples
Once configured, you can interact with your Airtable data naturally:
๐ท TypeScript Development
import {
AirtableMCPServer,
ListRecordsInput,
AnalyzeDataPrompt
} from '@rashidazarang/airtable-mcp/types';
const server = new AirtableMCPServer();
// Type-safe data operations
const params: ListRecordsInput = {
table: 'Tasks',
maxRecords: 10,
filterByFormula: "Status = 'Active'"
};
const records = await server.handleToolCall('list_records', params);
// Type-safe AI analytics
const analysis: AnalyzeDataPrompt = {
table: 'Sales',
analysis_type: 'predictive',
confidence_level: 0.95
};
const insights = await server.handlePromptGet('analyze_data', analysis);
๐ฆ Natural Language Interactions
Basic Operations
"List all my accessible Airtable bases"
"Show me all records in the Projects table"
"Create a new task with priority 'High' and due date tomorrow"
"Update the status of task ID rec123 to 'Completed'"
"Delete all records where status is 'Archived'"
"What tables are in my base?"
"Search for records where Status equals 'Active'"
Webhook Operations (v1.4.0+)
"Create a webhook for my table that notifies https://my-app.com/webhook"
"List all active webhooks in my base"
"Show me the recent webhook payloads"
"Delete webhook ach123xyz"
Schema Management (v1.5.0+)
"List all my accessible Airtable bases"
"Show me the complete schema for this base"
"Describe the Projects table with all field details"
"Create a new table called 'Tasks' with Name, Priority, and Due Date fields"
"Add a Status field to the existing Projects table"
"What field types are available in Airtable?"
Batch Operations & Attachments (v1.6.0+)
"Create 5 new records at once in the Tasks table"
"Update multiple records with new status values"
"Delete these 3 records in one operation"
"Attach this image URL to the record's photo field"
"Who are the collaborators on this base?"
"Show me all shared views in this base"
๐ ๏ธ Available Tools (33 Total)
๐ Data Operations (7 tools)
| Tool | Description |
|---|---|
list_tables |
Get all tables in your base with schema information |
list_records |
Query records with optional filtering and pagination |
get_record |
Retrieve a single record by ID |
create_record |
Add new records to any table |
update_record |
Modify existing record fields |
delete_record |
Remove records from a table |
search_records |
Advanced search with Airtable formulas and sorting |
๐ช Webhook Management (5 tools)
| Tool | Description |
|---|---|
list_webhooks |
View all webhooks configured for your base |
create_webhook |
Set up real-time notifications for data changes |
delete_webhook |
Remove webhook configurations |
get_webhook_payloads |
Retrieve webhook notification history |
refresh_webhook |
Extend webhook expiration time |
๐ Schema Discovery (6 tools) - New in v1.5.0
| Tool | Description |
|---|---|
list_bases |
List all accessible Airtable bases with permissions |
get_base_schema |
Get complete schema information for any base |
describe_table |
Get detailed table info including all field specifications |
list_field_types |
Reference guide for all available Airtable field types |
get_table_views |
List all views for a specific table with configurations |
๐๏ธ Table Management (3 tools) - New in v1.5.0
| Tool | Description |
|---|---|
create_table |
Create new tables with custom field definitions |
update_table |
Modify table names and descriptions |
delete_table |
Remove tables (with safety confirmation required) |
๐ง Field Management (3 tools) - New in v1.5.0
| Tool | Description |
|---|---|
create_field |
Add new fields to existing tables with all field types |
update_field |
Modify field properties, names, and options |
delete_field |
Remove fields (with safety confirmation required) |
โก Batch Operations (4 tools) - New in v1.6.0
| Tool | Description |
|---|---|
batch_create_records |
Create up to 10 records at once for better performance |
batch_update_records |
Update up to 10 records simultaneously |
batch_delete_records |
Delete up to 10 records in a single operation |
batch_upsert_records |
Update existing or create new records based on key fields |
๐ Attachment Management (1 tool) - New in v1.6.0
| Tool | Description |
|---|---|
upload_attachment |
Attach files from public URLs to attachment fields |
๐๏ธ Advanced Views (2 tools) - New in v1.6.0
| Tool | Description |
|---|---|
create_view |
Create new views (grid, form, calendar, etc.) with custom configurations |
get_view_metadata |
Get detailed view information including filters and sorts |
๐ข Base Management (3 tools) - New in v1.6.0
| Tool | Description |
|---|---|
create_base |
Create new Airtable bases with initial table structures |
list_collaborators |
View base collaborators and their permission levels |
list_shares |
List shared views and their public configurations |
๐ค AI Intelligence Suite (10 prompts) - New in v3.0.0
| Prompt | Description | Enterprise Features |
|---|---|---|
analyze_data |
Advanced statistical analysis with ML insights | Confidence intervals, anomaly detection |
create_report |
Intelligent report generation with recommendations | Multi-stakeholder customization, ROI analysis |
data_insights |
Business intelligence and pattern discovery | Cross-table correlations, predictive indicators |
optimize_workflow |
AI-powered automation recommendations | Change management, implementation roadmaps |
smart_schema_design |
Database optimization with best practices | Compliance-aware (GDPR, HIPAA), scalability planning |
data_quality_audit |
Comprehensive quality assessment and fixes | Automated remediation, governance frameworks |
predictive_analytics |
Forecasting and trend prediction | Multiple algorithms, uncertainty quantification |
natural_language_query |
Process human questions intelligently | Context awareness, confidence scoring |
smart_data_transformation |
AI-assisted data processing | Quality rules, audit trails, optimization |
automation_recommendations |
Workflow optimization suggestions | Technical feasibility, cost-benefit analysis |
๐ง Advanced Configuration
Using with Smithery Cloud
For cloud-hosted MCP servers:
{
"mcpServers": {
"airtable": {
"command": "npx",
"args": [
"@smithery/cli",
"run",
"@rashidazarang/airtable-mcp",
"--token",
"YOUR_TOKEN",
"--base",
"YOUR_BASE_ID"
]
}
}
}
Direct Node.js Execution
If you cloned the repository:
{
"mcpServers": {
"airtable": {
"command": "node",
"args": [
"/path/to/airtable-mcp/airtable_simple.js",
"--token",
"YOUR_TOKEN",
"--base",
"YOUR_BASE_ID"
]
}
}
}
๐งช Testing
๐ท TypeScript Testing
Run the comprehensive TypeScript test suite:
# Install dependencies first
npm install
# Run TypeScript type checking
npm run test:types
# Run full TypeScript test suite
npm run test:ts
# Build and test TypeScript server
npm run build
npm run start:ts
๐ฆ JavaScript Testing
Run the comprehensive test suite to verify all 33 tools:
# Set environment variables first
export AIRTABLE_TOKEN=your_token
export AIRTABLE_BASE_ID=your_base_id
# Start the server
node airtable_simple.js &
# Run comprehensive tests (v1.6.0+)
./test_v1.6.0_comprehensive.sh
The TypeScript test suite validates:
- Type Safety: Compile-time validation of all interfaces
- Enterprise Testing: 33 tools with strict type checking
- AI Prompt Validation: All 10 AI templates with proper typing
- Error Handling: Type-safe error management
- Performance: Concurrent operations with type safety
- Integration: Full MCP protocol compliance
The JavaScript test suite validates:
- All 33 tools with real API calls
- Complete CRUD operations
- Advanced schema management
- Batch operations (create/update/delete multiple records)
- Attachment management via URLs
- Advanced view creation and metadata
- Base management and collaboration tools
- Webhook management
- Error handling and edge cases
- Security verification
- 100% test coverage
๐ Troubleshooting
"Connection Refused" Error
- Ensure the MCP server is running
- Check that port 8010 is not blocked
- Restart your MCP client
"Invalid Token" Error
- Verify your Personal Access Token is correct
- Check that the token has the required scopes
- Ensure no extra spaces in your credentials
"Base Not Found" Error
- Confirm your Base ID is correct
- Check that your token has access to the base
Port Conflicts
If port 8010 is in use:
lsof -ti:8010 | xargs kill -9
๐ Documentation
๐ท TypeScript Documentation
- ๐ TypeScript Examples - Complete type-safe usage examples
- ๐๏ธ Type Definitions - Comprehensive type definitions for all features
- ๐งช TypeScript Testing - Enterprise-grade testing framework
๐ฆ General Documentation
- ๐ Release Notes v3.1.0 - Latest TypeScript release
- Release Notes v1.6.0 - Major feature release
- Release Notes v1.5.0
- Release Notes v1.4.0
- Detailed Setup Guide
- Development Guide
- Security Notice
๐ฆ Version History
- v3.1.0 (2025-08-16) - ๐ท TypeScript Support: Enterprise-grade type safety, comprehensive type definitions, dual JS/TS distribution
- v3.0.0 (2025-08-16) - ๐ค Revolutionary AI Agent: 10 intelligent prompts, predictive analytics, natural language processing
- v2.2.3 (2025-08-16) - ๐ Security release: Final XSS vulnerability fixes and enhanced validation
- v2.2.0 (2025-08-16) - ๐ Major release: Complete MCP 2024-11-05 protocol implementation
- v1.6.0 (2025-08-15) - ๐ Major release: Added batch operations & attachment management (33 total tools)
- v1.5.0 (2025-08-15) - Added comprehensive schema management (23 total tools)
- v1.4.0 (2025-08-14) - Added webhook support and enhanced CRUD operations (12 tools)
- v1.2.4 (2025-08-12) - Security fixes and stability improvements
- v1.2.3 (2025-08-11) - Bug fixes and error handling
- v1.2.2 (2025-08-10) - Initial stable release
๐ Project Structure
airtable-mcp/
โโโ src/ # Source code
โ โโโ index.js # Main entry point
โ โโโ typescript/ # TypeScript implementation
โ โโโ javascript/ # JavaScript implementation
โ โโโ python/ # Python implementation
โโโ dist/ # Compiled TypeScript output
โโโ docs/ # Documentation
โ โโโ guides/ # User guides
โ โโโ releases/ # Release notes
โโโ tests/ # Test files
โโโ examples/ # Usage examples
โโโ types/ # TypeScript type definitions
๐ค Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
๐ License
MIT License - see LICENSE file for details
๐ Acknowledgments
- Built for the Model Context Protocol
- Powered by Airtable API
- Compatible with Claude Desktop and other MCP clients
๐ฎ Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
Version: 3.2.4 | Status: ๐ท TypeScript Fixed + ๐ค AI Agent | MCP Protocol: 2024-11-05 Complete | Type Safety: Enterprise-Grade | Intelligence: 10 AI Prompts | Security: Fully Patched (XSS Fixed) | Last Updated: September 9, 2025
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Topics
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
dbt MCP Server
Bridge dbt projects and AI agents with rich project context.
dbt MCP Server provides an implementation of the Model Context Protocol for dbt projects, enabling seamless integration between dbt and AI agents. It allows agents to access and understand the context of dbt Core, dbt Fusion, and dbt Platform projects. The tool supports connection to external AI products and offers resources for building custom agents. Documentation and examples are provided to facilitate adoption and integration.
- โญ 420
- MCP
- dbt-labs/dbt-mcp
Pica MCP Server
A Model Context Protocol (MCP) server for seamless integration with 100+ platforms via Pica.
Pica MCP Server provides a standardized Model Context Protocol (MCP) interface for interaction with a wide range of third-party services through Pica. It enables direct platform integrations, action execution, and intelligent intent detection while prioritizing secure environment variable management. The server also offers features such as code generation, form and data handling, and robust documentation for platform actions. It supports multiple deployment methods, including standalone, Docker, Vercel, and integration with tools like Claude Desktop and Cursor.
- โญ 8
- MCP
- picahq/mcp
Supabase MCP Server
Connect Supabase projects to AI assistants using the Model Context Protocol.
Supabase MCP Server enables direct, secure integration between Supabase projects and AI assistants such as Cursor, Claude, and Windsurf. Leveraging the Model Context Protocol, it provides standardized endpoints for external LLMs to perform tasks like managing tables, fetching configurations, and querying data on Supabase. The server supports OAuth 2.1 Dynamic Client Registration and offers easy setup with feature groups and popular client installers for local, cloud, and self-hosted environments.
- โญ 2,263
- MCP
- supabase-community/supabase-mcp
MXCP
Enterprise-Grade Model Context Protocol Framework for AI Applications
MXCP is an enterprise-ready framework that implements the Model Context Protocol (MCP) for building secure, production-grade AI application servers. It introduces a structured methodology focused on data modeling, robust service design, policy enforcement, and comprehensive testing, integrated with strong security and audit capabilities. The framework enables rapid development and deployment of AI tools, supporting both SQL and Python environments, with built-in telemetry and drift detection for reliability and compliance.
- โญ 49
- MCP
- raw-labs/mxcp
Kanboard MCP Server
MCP server for seamless AI integration with Kanboard project management.
Kanboard MCP Server is a Go-based server implementing the Model Context Protocol (MCP) for integrating AI assistants with the Kanboard project management system. It enables users to manage projects, tasks, users, and workflows in Kanboard directly via natural language commands through compatible AI tools. With built-in support for secure authentication and high performance, it facilitates streamlined project operations between Kanboard and AI-powered clients like Cursor or Claude Desktop. The server is configurable and designed for compatibility with MCP standards.
- โญ 15
- MCP
- bivex/kanboard-mcp
Firefly MCP Server
Seamless resource discovery and codification for Cloud and SaaS with Model Context Protocol integration.
Firefly MCP Server is a TypeScript-based server implementing the Model Context Protocol to enable integration with the Firefly platform for discovering and managing resources across Cloud and SaaS accounts. It supports secure authentication, resource codification into infrastructure as code, and easy integration with tools such as Claude and Cursor. The server can be configured via environment variables or command line and communicates using standardized MCP interfaces. Its features facilitate automation and codification workflows for cloud resource management.
- โญ 15
- MCP
- gofireflyio/firefly-mcp
Didn't find tool you were looking for?