Skip to main content
Glama

Medicus CRM MCP Server

A Model Context Protocol (MCP) server for the Medicus CRM system, supporting both local STDIO and remote HTTP access.

Features

  • 18 CRM tools for managing companies, contacts, and related data

  • Supabase integration for data persistence

  • Local STDIO transport for development (full functionality)

  • Remote HTTP transport for production deployment (tool listing + basic protocol)

  • Token-based authentication for security

Related MCP server: Company Records

Local Development

Prerequisites

  • Node.js 18+

  • Supabase project with service role key

Setup

  1. Install dependencies:

    npm install
  2. Create environment file:

    cp env.example .env.local
  3. Configure your environment variables in .env.local:

    SUPABASE_URL=your_supabase_url_here
    SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key_here
    MCP_TOKEN=your_long_random_token_here

Running Locally

STDIO Mode (for local MCP clients)

npm run mcp:stdio

HTTP Mode (for testing remote access)

npm run dev

Then test with MCP Inspector:

npx @modelcontextprotocol/inspector http://localhost:3000/api/mcp?token=your_token

Note: The HTTP endpoint currently supports tool listing and basic MCP protocol. For full tool execution, use the STDIO mode locally.

Deployment to Vercel

  1. Install Vercel CLI:

    npm i -g vercel
  2. Deploy:

    vercel
  3. Set environment variables in Vercel dashboard:

    • SUPABASE_URL

    • SUPABASE_SERVICE_ROLE_KEY

    • MCP_TOKEN (optional)

  4. Your MCP server will be available at:

    https://your-app.vercel.app/api/mcp?token=your_token

Adding to Claude

In Claude Desktop or Web:

  1. Go to Settings → Connectors

  2. Add custom connector

  3. Enter your Vercel URL: https://your-app.vercel.app/api/mcp?token=your_token

Tool Registration

The main tool registration logic is in lib/register-crm-tools.js. This file contains:

  • Helper functions for error handling and data manipulation

  • All 18 CRM tool registrations

  • Supabase integration logic

To add new tools or modify existing ones, edit this file. The changes will be available in both STDIO and HTTP modes.

Security

  • The server uses Supabase service role key for database access

  • Optional token-based authentication prevents unauthorized access

  • For production, consider implementing OAuth instead of simple tokens

Architecture

├── lib/
│   ├── register-crm-tools.js    # Shared tool registration logic
│   └── supabase.js              # Supabase client factory
├── bin/
│   └── stdio.mjs                # Local STDIO server
├── app/
│   └── api/
│       └── mcp/
│           └── route.ts         # HTTP MCP endpoint
└── package.json                 # Dependencies and scripts

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Integrates CRM data with AI agents to manage leads, track pipeline statistics, and search price catalogs via Supabase. It enables automated lead creation, stage updates, and history tracking through natural language commands.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Exposes a fictional B2B CRM database (companies, contacts, deals) as callable MCP tools, enabling AI agents to answer natural-language questions about company records, contacts, and pipeline data.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to interact with a CRM covering companies, people, leads, deals, and more, with role checks, scoped agent keys, approval gates, and a shared audit trail.
    AGPL 3.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to manage CRM data including companies, contacts, prospects, pipelines, forecasts, and tasks via typed MCP tools, with local SQLite storage and a JSON CLI.
    MIT