What transport modes does Prometheus MCP Server support?
It supports SSE (Server-Sent Events) by default and can be switched to stdio mode by changing the `MCP_SERVER_TRANSPORT` environment variable.
@shaxiaozz
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"prometheus-mcp-server": {
"command": "docker",
"args": [
"-d",
"--name",
"prometheus-mcp-server",
"-e",
"PROMETHEUS_URL",
"shaxiaozz/prometheus-mcp-server:latest"
],
"env": {
"PROMETHEUS_URL": "http://your-prometheus-server:9090"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A Go-based MCP server that integrates with Prometheus, currently supporting only SSE transport mode. It is for users who want to interact with Prometheus metrics through the Model Context Protocol.
Run the Docker container with environment variables for your Prometheus URL and optional authentication (basic auth or Bearer Token), then configure your MCP client (e.g., Cursor Desktop) with the SSE URL shown in the container logs. The server can be toggled to stdio mode by changing MCP_SERVER_TRANSPORT.
It supports SSE (Server-Sent Events) by default and can be switched to stdio mode by changing the `MCP_SERVER_TRANSPORT` environment variable.
Authentication is configured via environment variables: either `PROMETHEUS_USERNAME` and `PROMETHEUS_PASSWORD` for basic auth, or `PROMETHEUS_TOKEN` for Bearer Token auth.
Yes, the primary deployment method is through Docker. The README provides a Docker run command and instructions for building the image yourself.
Yes, you can clone the repository and run `docker build -t prometheus-mcp-server .` to create a custom image.
After starting the container, run `docker logs prometheus-mcp-server` to see the URL (e.g., `http://10.0.0.1:8000/sse`).
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

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

Publish the website your AI assistant just built, straight from the conversation. Static sites, your own domain, one payment, no subscription.

The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
评论