twenty-mcp-server
A standalone MCP server that integrates with Twenty CRM to provide AI-powered CRM capabilities, enabling CRUD operations and real-time synchronization.
README
Twenty MCP Server
A standalone MCP (Model Context Protocol) server that integrates with Twenty CRM to provide AI-powered customer relationship management capabilities.
Overview
This server enables seamless AI interaction with Twenty CRM through the Model Context Protocol, allowing AI assistants to perform CRM operations, analyze data, and provide intelligent insights.
Features
- Complete CRM Integration: Full CRUD operations for all Twenty CRM entities
- Real-time Synchronization: WebSocket-based real-time updates
- Schema Awareness: Dynamic adaptation to custom fields and objects
- Intelligent API Selection: Optimized GraphQL and REST API usage
- Production Ready: Docker containerization and monitoring
Quick Start
Prerequisites
- Node.js 18+
- Docker and Docker Compose
- Git
Installation & Setup
- Clone and install:
git clone <repository-url>
cd twenty-mcp-server
npm install
- Start Twenty CRM:
# Smart start (only starts what's needed)
npm run twenty:quick
-
Create workspace:
- Open http://localhost:3000
- Create workspace and user account
- Generate API key in Settings > API
-
Configure MCP server:
# Setup environment file
npm run twenty:setup
# Edit .env file with your API key
- Test integration:
# Test API discovery
npm run discover
# Start MCP server
npm run dev
Configuration
The setup script creates an .env file with:
TWENTY_API_URL: Local Twenty instance (http://localhost:3000)TWENTY_API_KEY: Your Twenty API key
See .env.example for all configuration options.
Development
Development Scripts
MCP Server
npm run dev- Start MCP server in development modenpm run build- Build the TypeScript projectnpm run test- Run testsnpm run lint- Run lintingnpm run discover- Run API discovery tool (requires Twenty CRM)
Twenty CRM (for testing)
npm run twenty:quick- Smart start Twenty CRM (recommended)npm run twenty:status- Check Twenty statusnpm run twenty:setup- Configure MCP environmentnpm run twenty:logs- View Twenty logsnpm run twenty:stop- Stop Twenty services
Project Structure
src/
�� server.ts # Main MCP server entry point
�� twenty-client/ # Twenty CRM API client
�� tools/ # MCP tools implementation
�� types/ # TypeScript type definitions
�� utils/ # Utilities and configuration
Deployment
Docker
Build and run with Docker:
docker build -t twenty-mcp-server .
docker run -d --env-file .env -p 3001:3001 twenty-mcp-server
Docker Compose
docker-compose up -d
License
MIT License - see LICENSE file for details.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
Documentation
- Quick Start Guide - Get running in 5 minutes
- Twenty Scripts Guide - Complete script documentation
- API Discovery Reports - Generated after running
npm run discover
Troubleshooting
- Twenty won't start:
npm run twenty:logs - Connection issues:
npm run twenty:status - Fresh restart:
npm run twenty:start(resets everything) - View help:
npm run twenty:help
Support
For support and documentation, see the documentation links above or open an issue on GitHub.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.