Twenty CRM

Containerized stack combining Twenty CRM with an MCP Server for AI-enabled integrations and automation.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "denisalmeida-twenty-crm-mcp": {
      "command": "node",
      "args": [
        "mcp/index.js"
      ],
      "env": {
        "PORT": "3000",
        "TWENTY_API_KEY": "YOUR_API_KEY",
        "TWENTY_BASE_URL": "https://twenty.ambienz.com.br/rest"
      }
    }
  }
}

You run a combined Twenty CRM and MCP Server stack that enables AI-powered automations and advanced context handling. This server lets you manage customers, companies, opportunities, notes, tasks, conversations, and invoices while connecting to AI-driven tools through the MCP interface for streamlined workflows.

How to use

You configure your client to talk to the MCP Server by pointing it at the MCP endpoint and supplying your API key. The MCP Server exposes an HTTP REST-compatible surface through the Twenty CRM REST API, and it accepts commands via its MCP endpoint to run tools, stream events, and manage context. Use the MCP client to execute tools, subscribe to updates via Server-Sent Events, and push or query context as part of automated workflows.

How to install

Prerequisites you need before starting include Docker and Docker Compose installed on your host, and Node.js if you plan to run any local MCP components outside of Docker.

Step by step to deploy the stack locally via Docker Compose:

# Copy environment template
cp .env.example .env

# Start all services in detached mode
docker-compose up -d

# Check service status
docker-compose ps

# View logs for the MCP server component
docker-compose logs -f ambienz-twenty-mcp-server

Configuration and run notes

The MCP Server runs as a separate container and exposes its services on port 3001. The Twenty CRM application is available at the configured base URL, and you provide runtime configuration via environment variables.

Important environment variables you must set to use the MCP server effectively are listed here. You use these when starting the MCP server in your local environment or in your deployment environment.

# Required by MCP client to access Twenty CRM REST API
TWENTY_API_KEY=your-api-key
TWENTY_BASE_URL=https://twenty.ambienz.com.br/rest
PORT=3000

Security considerations

Protect your API key and ensure communications with Twenty CRM and the MCP Server occur over TLS. Do not expose administration endpoints publicly. Use firewalls or private networking between services and rotate keys periodically.

Troubleshooting

If you cannot reach the MCP endpoint, verify that the MCP container is running and listening on port 3001. Check the logs for the ambienz-twenty-mcp-server service for startup errors, and ensure the TWENTY_BASE_URL and TWENTY_API_KEY values are correct.

Notes

This setup integrates three containerized services: Twenty CRM, Twenty Worker, and the MCP Server. The MCP Server interacts with the AI and automation tooling to enhance CRM workflows and context management.

Available tools

healthCheck

Performs a health check on the MCP server to ensure it is running and reachable.

runTool

Executes a specific tool by name via the MCP API at POST /tools/:toolName.

mcpEndpoint

Receives MCP events via the Server-Sent Events endpoint to stream updates and context changes.