MCP Server for Prometheus
@MCP-Mirror
About MCP Server for Prometheus
Mirror of
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"CaesarYangs_prometheus_mcp_server": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Server for Prometheus?
MCP Server for Prometheus is a Model Context Protocol server that lets Large Language Models retrieve and analyze metric data from Prometheus databases. It provides pre‑defined tool functions for fetching metrics, performing analysis, searching usage patterns, and executing complex PromQL queries.
How to use MCP Server for Prometheus?
Create a Python virtual environment, install the required packages from requirements.txt, and set the PROMETHEUS_HOST environment variable (default http://localhost:9090). You can then run server.py either as a standalone server (using uv or python3) or configure it in Claude Desktop by adding the server entry to claude_desktop_config.json.
Key features of MCP Server for Prometheus
- Retrieve metric names and descriptions from Prometheus
- Fetch and analyze specific metric data by name
- Analyze metric data within custom time ranges
- Execute advanced PromQL queries for in‑depth exploration
Use cases of MCP Server for Prometheus
- Fetch specific metrics or ranges of data from a Prometheus instance
- Perform statistical analysis on retrieved metric values
- Search for and explore metric usage patterns
- Run complex PromQL queries for detailed data exploration
FAQ from MCP Server for Prometheus
What runtime environment is required?
The server runs inside a Python virtual environment (venv). All packages in requirements.txt must be installed into that venv.
How do I configure the server for Claude Desktop?
Add an entry to your Claude Desktop configuration file (e.g., ~/Library/Application Support/Claude/claude_desktop_config.json on macOS) with the command uv, the path to the server directory, and the PROMETHEUS_HOST environment variable.
How can I run the server standalone?
Use either uv --directory /path/to/prometheus_mcp_server run server.py or python3 server.py from the project directory.
What environment variable controls the Prometheus host?
The `PROMETHE
Frequently asked questions
What runtime environment is required?
The server runs inside a Python virtual environment (venv). All packages in `requirements.txt` must be installed into that venv.
How do I configure the server for Claude Desktop?
Add an entry to your Claude Desktop configuration file (e.g., `~/Library/Application Support/Claude/claude_desktop_config.json` on macOS) with the command `uv`, the path to the server directory, and the `PROMETHEUS_HOST` environment variable.
How can I run the server standalone?
Use either `uv --directory /path/to/prometheus_mcp_server run server.py` or `python3 server.py` from the project directory.
What environment variable controls the Prometheus host?
The `PROMETHE
Basic information
More Developer Tools MCP servers
MCP Inspector
modelcontextprotocolVisual testing tool for MCP servers
Serena
oraiosA powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Reelier
Maxime HouleAgents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
Unity MCP (Server + Plugin)
IvanMurzakAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for fr
Comments