mcp -crm
MCP server from zeeshan8281/mcp-server-crm
claude mcp add --transport stdio zeeshan8281-mcp-server-crm node /path/to/crm-mcp/server.js \ --env PORT="3000" \ --env SUPABASE_KEY="your-supabase-anon-key" \ --env SUPABASE_URL="https://your-project.supabase.co"
How to use
This MCP server provides AI-powered CRM capabilities via the Model Context Protocol. It exposes a suite of tools for managing contacts, analyzing performance, and generating AI-driven insights. Tools include get_contacts, add_contact, get_top_clients, search_contacts, get_ai_insights, predict_revenue, get_relationship_map, get_analytics, get_recommendations, and ai_chat. You can invoke these tools through an MCP client (such as Cursor or Claude Desktop) to perform tasks like retrieving contacts with AI scoring, adding new contacts with insights, or querying for top clients and revenue trends. The server integrates with a Supabase backend for data storage and real-time analytics, enabling richer context for AI agents.
How to install
Prerequisites:
- Node.js 18+ installed on your machine
- Access to a Supabase project (URL and anon/public key)
- MCP-compatible client (e.g., Cursor, Claude Desktop)
- Install dependencies
npm install
- Create a .env file (or set environment variables in your deployment) with your Supabase credentials and optional server port:
# Supabase Configuration
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-supabase-anon-key
# Optional: Server Configuration
PORT=3000
- Set up the database (example schema included in README):
CREATE TABLE contacts (
id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
name TEXT NOT NULL,
email TEXT NOT NULL,
company TEXT,
revenue INTEGER DEFAULT 0,
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW()
);
ALTER TABLE contacts ENABLE ROW LEVEL SECURITY;
CREATE POLICY "Allow public access" ON contacts FOR ALL USING (true);
- Run the MCP server (example using the suggested command from the README):
# Start the MCP server (adjust path to your server.js)
npm run start
# Or run directly:
node /path/to/crm-mcp/server.js
- Connect with an MCP client by configuring the client’s mcpServers setting to point to the running server. Example configuration uses the crm-assistant server:
{
"mcpServers": {
"crm-assistant": {
"command": "node",
"args": ["/path/to/crm-mcp/server.js"],
"env": {
"SUPABASE_URL": "https://your-project.supabase.co",
"SUPABASE_KEY": "your-supabase-key"
}
}
}
}
Additional notes
Environment variables must be kept secure. Ensure your Supabase URL and anon key are not exposed in client-side code. You can customize the PORT, database schema, and policies to match your security requirements. If tools fail to load, verify the MCP protocol is correctly implemented and that the StdioServerTransport is reachable by your MCP client. Regularly update dependencies and monitor Supabase quotas to avoid service interruptions.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.