Twenty CRM MCP Server
Connects Twenty CRM with AI assistants like Claude, enabling natural language interactions with customer data. Supports CRUD operations for people, companies, tasks, notes, and advanced search.
README
<div align="center">
🤖 Twenty CRM MCP Server
Transform your CRM into an AI-powered assistant
A Model Context Protocol server that connects Twenty CRM with Claude and other AI assistants, enabling natural language interactions with your customer data.
🚀 Quick Start • 📖 Usage Examples • 🛠️ API Reference • 🤝 Contributing
</div>
✨ Features
<table> <tr> <td width="50%">
🔄 Complete CRUD Operations
Create, read, update, and delete people, companies, tasks, and notes with simple commands
🧠 Dynamic Schema Discovery
Automatically adapts to your Twenty CRM configuration and custom fields
🔍 Advanced Search
Search across multiple object types with intelligent filtering and natural language queries
</td> <td width="50%">
📊 Metadata Access
Retrieve schema information and field definitions dynamically
💬 Natural Language Interface
Use conversational commands to manage your CRM data effortlessly
⚡ Real-time Updates
All changes sync immediately with your Twenty CRM instance
</td> </tr> </table>
🚀 Installation
Prerequisites
- Node.js 18 or higher
- A Twenty CRM instance (cloud or self-hosted)
- Claude Desktop or compatible MCP client
Setup
- Clone the repository:
git clone https://github.com/mhenry3164/twenty-crm-mcp-server.git
cd twenty-crm-mcp-server
- Install dependencies:
npm install
-
Get your Twenty CRM API key:
- Log in to your Twenty CRM workspace
- Navigate to Settings → API & Webhooks (under Developers)
- Generate a new API key
-
Configure Claude Desktop:
Add the server to your claude_desktop_config.json:
{
"mcpServers": {
"twenty-crm": {
"command": "node",
"args": ["/path/to/twenty-crm-mcp-server/index.js"],
"env": {
"TWENTY_API_KEY": "your_api_key_here",
"TWENTY_BASE_URL": "https://api.twenty.com"
}
}
}
}
For self-hosted Twenty instances, change TWENTY_BASE_URL to your domain.
- Restart Claude Desktop to load the new server.
💬 Usage
Once configured, you can use natural language to interact with your Twenty CRM:
👥 People Management
"List the first 10 people in my CRM"
"Create a new person named John Doe with email john@example.com"
"Update Sarah's job title to Senior Developer"
"Find all people working at tech companies"
🏢 Company Management
"Show me all companies with more than 100 employees"
"Create a company called Tech Solutions with domain techsolutions.com"
"Update Acme Corp's annual revenue to $5M"
✅ Task Management
"Create a task to follow up with John next Friday"
"Show me all overdue tasks"
"Mark the task 'Call client' as completed"
📝 Notes & Search
"Add a note about my meeting with the client today"
"Search for any records mentioning 'blockchain'"
"Find all contacts without LinkedIn profiles"
🛠️ API Reference
The server provides the following tools:
<details> <summary><strong>👥 People Operations</strong></summary>
create_person- Create a new personget_person- Get person details by IDupdate_person- Update person informationlist_people- List people with filteringdelete_person- Delete a person
</details>
<details> <summary><strong>🏢 Company Operations</strong></summary>
create_company- Create a new companyget_company- Get company details by IDupdate_company- Update company informationlist_companies- List companies with filteringdelete_company- Delete a company
</details>
<details> <summary><strong>✅ Task Operations</strong></summary>
create_task- Create a new taskget_task- Get task details by IDupdate_task- Update task informationlist_tasks- List tasks with filteringdelete_task- Delete a task
</details>
<details> <summary><strong>📝 Note Operations</strong></summary>
create_note- Create a new noteget_note- Get note details by IDupdate_note- Update note informationlist_notes- List notes with filteringdelete_note- Delete a note
</details>
<details> <summary><strong>🔍 Metadata & Search</strong></summary>
get_metadata_objects- Get all object types and schemasget_object_metadata- Get metadata for specific objectsearch_records- Search across multiple object types
</details>
⚙️ Configuration
Environment Variables
TWENTY_API_KEY(required): Your Twenty CRM API keyTWENTY_BASE_URL(optional): Twenty CRM base URL (defaults tohttps://api.twenty.com)
Custom Fields
The server automatically discovers and supports custom fields in your Twenty CRM instance. No configuration changes needed when you add new fields.
🤝 Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
Development
- Clone the repo:
git clone https://github.com/mhenry3164/twenty-crm-mcp-server.git
cd twenty-crm-mcp-server
- Install dependencies:
npm install
- Set up environment variables:
cp .env.example .env
# Edit .env with your API key
- Test the server:
npm test
🐛 Troubleshooting
Common Issues
Authentication Error: Verify your API key is correct and has appropriate permissions.
Connection Failed: Check that your TWENTY_BASE_URL is correct (especially for self-hosted instances).
Field Not Found: The server automatically discovers fields. If you're getting field errors, try getting the metadata first: "Show me the available fields for people"
📄 License
MIT License - see LICENSE file for details.
🙏 Acknowledgments
- Twenty CRM for providing an excellent open-source CRM
- Anthropic for the Model Context Protocol
- The MCP community for inspiration and examples
🔗 Links
<div align="center">
Made with ❤️ for the open-source community
⭐ Star this repo if you find it helpful!
</div>
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.