prometheus_mcp_server

概述

这个基于Python的MCP服务器使大型语言模型能够从Prometheus数据库检索和分析指标数据。它提供用于获取特定指标、执行统计分析、搜索指标使用模式和执行复杂PromQL查询的工具。服务器支持数据分析的自定义时间范围，并设计为可与Claude Desktop等AI环境集成。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• retrieve_metric_info

  Retrieve comprehensive metric information including names and descriptions from Prometheus

  试试:Show me all available metrics in Prometheus试试:What metrics are currently being tracked?
• fetch_metric_data

  Fetch and analyze specific metric data using metric names

  试试:Get CPU usage metrics for the last hour试试:Retrieve memory consumption metrics for my application
• analyze_metric_data

  Analyze metric data within custom time ranges

  试试:Analyze response time metrics for the last 24 hours试试:Compare error rates between this week and last week
• execute_promql_query

  Execute advanced PromQL queries for in-depth data exploration

  试试:Run PromQL query to find top 5 slowest endpoints试试:Execute PromQL to get average request latency per minute

说明：Tool names were inferred from the capabilities section of the README as there is no explicit 'Tools' section listing the MCP functions. The actual tool names and signatures are not explicitly documented in the README.

可对比工具

安装

npx -y @smithery/cli install @CaesarYangs/prometheus_mcp_server --client claude

cd ./src/prometheus_mcp_server
python3 -m venv .venv
source .venv/bin/activate

pip install -r requirements.txt

{
    "mcpServers": {
        "prometheus": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/prometheus_mcp_server",
                "run",
                "server.py"
            ],
            "env": {
                "PROMETHEUS_HOST": "http://localhost:9090"
            }
        }
    }
}

FAQ

支持哪些Prometheus操作？

该服务器支持检索指标信息、获取和分析特定指标、分析自定义时间范围内的数据以及执行PromQL查询。标签过滤被标记为开发中。

我能否将其与其他MCP客户端一起使用？

是的，该服务器可以作为独立服务器与任何MCP客户端一起使用。README提供了在Cursor环境和作为独立服务器中使用的说明。

prometheus_mcp_server 对比