如何设置 Prometheus 地址?
通过环境变量 `PROMETHEUS_URL` 设置 Prometheus 端点,例如 `export PROMETHEUS_URL=http://your-prometheus:9090`。
@qingshanyuluo
Basic information
一个简化版的Prometheus MCP服务器,用于收集和暴露MCP服务器的指标
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"prometheus-mcp-server-qingshanyuluo": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"node",
"build/index.js"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Prometheus MCP 服务器是一个简化版的 MCP 服务器,用于查询 Prometheus 指标并提供 AI 分析。它通过 MCP 工具暴露 Prometheus 的查询能力,方便 AI 代理或客户端集成。
设置环境变量 PROMETHEUS_URL 指定 Prometheus 端点,然后运行 go run cmd/server/main.go sse 启动服务器,默认监听 :8081 端口,通过 /sse 路径暴露 SSE 连接。MCP 客户端可通过配置 mcpServers 中的 url 为 http://localhost:8081/sse 连接使用。
通过环境变量 `PROMETHEUS_URL` 设置 Prometheus 端点,例如 `export PROMETHEUS_URL=http://your-prometheus:9090`。
服务器默认在 `:8081` 端口启动,可通过代码或启动参数修改(当前默认固定)。
支持即时查询(`query`)、范围查询(`query_range`)以及带图表的范围查询(`query_chart`)。
在 MCP 客户端配置文件中添加 `mcpServers` 项,指定 `url` 为服务器的 SSE 地址,例如 `http://localhost:8081/sse`。
所有工具查询结果均以 JSON 格式返回,`query_chart` 额外返回 base64 编码的 PNG 图片。

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott


OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
Comments