drio
Open app

MCP Server for Prometheus

Source

Mirror of

Catalog onlyCatalog onlySTDIO

Overview

MCP Server for Prometheus is a Model Context Protocol (MCP) server designed to retrieve and analyze data from Prometheus databases, enabling Large Language Models (LLMs) to perform various data-related tasks.

To use the MCP Server, set up a Python virtual environment, install the required packages, and configure your client application to connect to the server. You can run the server either through a command line or as part of a client application.

  • Data Retrieval: Fetch specific metrics or ranges of data from Prometheus. - Metric Analysis: Perform statistical analysis on retrieved metrics. - Usage Search: Explore metric usage patterns. - Complex Querying: Execute advanced PromQL queries for in-depth data exploration.
  1. Retrieving and analyzing performance metrics for applications.
  2. Executing complex queries to gain insights from large datasets.
  3. Integrating with AI models to enhance data-driven decision-making.

Add to your AI client

Use these steps to connect MCP Server for Prometheus in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "caesaryangs-prometheus-mcp-server-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-caesaryangs-prometheus-mcp-server-mcp-mirror"
      ]
    }
  }
}

FAQ

What is the purpose of the MCP Server?

The MCP Server allows for efficient data retrieval and analysis from Prometheus, facilitating advanced data operations for LLMs.

How do I install the MCP Server?

You need to set up a Python virtual environment and install the required packages listed in the requirements.txt file.

Can I run the MCP Server standalone?

Yes, you can run the MCP Server independently using the provided command line instructions.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":738,"uuid":"0722fd0c-55a5-492e-bfd3-30e8c865b049","name":"CaesarYangs_prometheus_mcp_server","title":"MCP Server for Prometheus","description":"Mirror of","avatar_url":"https://avatars.githubusercontent.com/u/192820360?v=4","created_at":"2024-12-30T03:28:26.575Z","updated_at":"2025-02-23T07:16:03.267Z","status":"created","author_name":"MCP-Mirror","author_avatar_url":"https://avatars.githubusercontent.com/u/192820360?v=4","tags":"mcp,prometheus,data-retrieval","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/MCP-Mirror/CaesarYangs_prometheus_mcp_server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data