MCP Server Prometheus

🚀 mcp-server-prometheus

An MCP server for interacting with Prometheus metrics and data.

This is a TypeScript-based MCP server that implements a Prometheus API interface. It provides a bridge between Claude and your Prometheus server through the Model Context Protocol (MCP).

🎥 Demo

✨ Features

Resources

• List and access Prometheus metric schemas.
• Each metric resource provides:
  • Metric name and description.
  • Detailed metadata from Prometheus.
  • Statistical information (count, minimum, maximum).
• JSON MIME type for structured data access.

Current Capabilities

• List all available Prometheus metrics and their descriptions.
• Read detailed metric information, including:
  • Metadata and help text.
  • Current statistical data (count value, minimum, maximum).
• Support for basic authentication for protected Prometheus instances.

⚙️ Configuration

The server requires the following environment variables:

• PROMETHEUS_URL: The base URL of your Prometheus instance.

Optional authentication configuration:

• PROMETHEUS_USERNAME: The username for basic authentication (if required).
• PROMETHEUS_PASSWORD: The password for basic authentication (if required).

💻 Development

Install dependencies:

npm install

Build the server:

npm run build

Develop with automatic rebuild:

npm run watch

📦 Installation

To use with Claude Desktop, add the server configuration:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server-prometheus": {
      "command": "/path/to/mcp-server-prometheus/build/index.js",
      "env": {
        "PROMETHEUS_URL": "http://your-prometheus-instance:9090"
      }
    }
  }
}

Debugging

Since MCP servers communicate via standard input and output, debugging can be challenging. We recommend using MCP Inspector:

npm run inspector

The Inspector will provide a URL to access the debugging tools in the browser.

📚 API Structure

The server exposes Prometheus metrics through the following URI structure:

• Base URI: http://your-prometheus-instance:9090
• Metric URI: http://your-prometheus-instance:9090/metrics/{metric_name}

Each metric resource returns JSON data containing the following:

• Metric name.
• Metadata (help text, type).
• Current statistical information (count, minimum, maximum).