Prometheus MCP Server 7t1

🚀 Prometheus MCP Server

This is a Model Context Protocol (MCP) server for interacting with Prometheus metrics and data. It serves as a bridge that enables Claude to interact with your Prometheus server via the Model Context Protocol (MCP).

🚀 Quick Start

This TypeScript-based MCP server implements the Prometheus API interface, allowing Claude to interact with your Prometheus server through the Model Context Protocol (MCP).

✨ Features

• Instant Query: Execute PromQL queries at a specific time point.
• Range Query: Execute PromQL queries within a specific time range.
• Series Discovery: Find series data based on label matchers.
• Label Exploration: Get values of specific labels.
• Metadata Access: Get metadata of metrics.
• Target Information: Get information about scraping targets.
• Alerts and Rules: Get information about alerts and recording rules.
• Status Information: Get the status information of the Prometheus server.

📦 Installation

# Global installation
npm install -g prometheus-mcp-server

# Or local installation
npm install prometheus-mcp-server

# Or run with npx without installation
npx prometheus-mcp-server

💻 Usage Examples

Basic Usage

To use it in 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": {
    "prometheus-mcp-server": {
      "command": "/path/to/prometheus-mcp-server/build/index.js",
      "env": {
        "PROMETHEUS_HOST": "http://your-prometheus-instance:9090"
      }
    }
  }
}

Advanced Usage

You can also use npx in the Claude Desktop configuration:

{
  "mcpServers": {
    "prometheus-mcp-server": {
      "command": "npx prometheus-mcp-server",
      "env": {
        "PROMETHEUS_HOST": "http://your-prometheus-instance:9090"
      }
    }
  }
}

📚 Documentation

Configuration

The server requires the following environment variables:

Available Functions

The server provides the following functions:

• mcp__instant_query: Execute an instant PromQL query.
• mcp__range_query: Execute a PromQL query within a time range.
• mcp__get_series: Find series data based on label matchers.
• mcp__get_label_values: Get values of a specific label.
• mcp__get_metadata: Get metadata of metrics.
• mcp__get_targets: Get information about scraping targets.
• mcp__get_alerts: Get alert information.
• mcp__get_rules: Get information about recording and alert rules.
• mcp__get_status: Get the status information of the Prometheus server.

Development

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm start

# Debug
npm run dev:debug

Debugging

Since the MCP server communicates via stdio, debugging can be challenging. You can use the following npm scripts for debugging:

# Inspection mode
npm run inspect

# Inspection with breakpoints
npm run inspect-debug

📄 License

ISC

💡 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.