mcpulse

MCPulse is an open-source analytics and observability platform designed to provide visibility into MCP servers. It collects usage, performance, error, and business metrics from MCP servers and presents them in a centralized dashboard. You can connect MCP servers via the Zero-Code MCPulse Proxy, which adds analytics to any MCP server without code changes, or by running the MCPulse server alongside your MCP infrastructure using the provided Docker setup. Use the dashboard to monitor server health, query MCP data, and gain insights into how clients interact with your MCP services. The platform also offers SDK integrations (Python and Go, with Node.js/TypeScript support coming soon) to push or pull metrics and event data, enabling you to extend observability into your existing MCP deployments.

Prerequisites:

• Docker and docker-compose installed on your host
• curl or wget for downloading configuration files

Step-by-step installation:

1. Prepare the environment
   • Ensure Docker is running on your machine.
2. Download configuration files
   • curl -O https://raw.githubusercontent.com/sirrobot01/mcpulse/main/docker-compose.yml
   • curl -o config.yaml https://raw.githubusercontent.com/sirrobot01/mcpulse/main/config.yaml.example
3. Start MCPulse
   • docker compose up -d
4. Access the dashboard
   • Open http://localhost:8080 in your web browser
5. Optional: Enable additional MCP integrations
   • Explore the integration options in the dashboard or via the provided SDKs (Python, Go; Node.js/TypeScript coming soon) to connect your MCP servers and begin collecting analytics.

Tips and common considerations:

• The recommended deployment method is via Docker using docker-compose as shown in the Quick Start. If you modify docker-compose.yml, ensure the port mappings and environment variables align with your environment.
• By default, MCPulse exposes the dashboard on http://localhost:8080. If running behind a reverse proxy or in a cloud environment, adjust the port and host bindings accordingly.
• If you use the MCPulse Proxy to instrument an existing MCP server, you can add analytics without modifying your MCP server code.
• Check the documentation linked in the README for advanced configuration, data retention settings, and scaling guidance.
• Ensure network access between your MCP servers and the MCPulse instance to enable proper data collection.