mcp-server-prometheus

Overview

This MCP server provides a bridge between Claude and Prometheus, allowing users to access and interact with Prometheus metrics through the Model Context Protocol. It implements a TypeScript-based interface to query Prometheus metrics, offering features like listing available metrics, accessing detailed metric information, and supporting basic authentication for secured instances. The server handles resource listing with JSON mime types and provides access to statistical information about each metric.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• list_metrics

  List all available Prometheus metrics with descriptions

  Try:List all available Prometheus metricsTry:What metrics are available in my Prometheus instance?
• get_metric_info

  Get detailed information about a specific Prometheus metric

  Try:Get detailed information about the CPU usage metricTry:Show metadata for the memory usage metric

Comparable tools

Installation

npm install

npm run build

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

FAQ

What authentication methods does this server support?

The server supports basic authentication for secured Prometheus instances using PROMETHEUS_USERNAME and PROMETHEUS_PASSWORD environment variables.

How do I debug the MCP server?

The server recommends using the MCP Inspector for debugging. Run 'npm run inspector' which provides a URL to access debugging tools in your browser.

Compare mcp-server-prometheus with