Prometheus

🚀 Prometheus MCP Server

A Model Context Protocol (MCP) server for retrieving data from the Prometheus database. This MCP server enables Large Language Models (LLMs) to call utility functions that perform tasks such as retrieving large amounts of metric data, searching for metric usage, executing complex queries, and more. It also provides enhanced control over usage through predefined routes.

• Data Retrieval: Fetch specific metrics or data within a specific time frame from Prometheus.
• Metric Analysis: Conduct statistical analysis on the retrieved metrics.
• Usage Search: Find and explore metric usage patterns.
• Complex Queries: Execute advanced PromQL queries for in-depth data exploration.

✨ Features

✅ Retrieve comprehensive metric information from Prometheus, including names and descriptions. ✅ Fetch and analyze specific metric data by metric name. ✅ Analyze metric data within a custom time range. 🚧 Filter and match data using specific labels (Under development). ⏳ More features are planned...

🚀 Quick Start

Running the MCP requires a Python virtual environment (venv). All packages should be installed in this venv so that the MCP server can start automatically.

📦 Installation via Smithery

To automatically install the Prometheus MCP Server for Claude Desktop via Smithery:

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

📦 Manual Installation

Prepare the Python Environment

cd ./src/prometheus_mcp_server
python3 -m venv .venv

# For Linux/macOS:
source .venv/bin/activate

# For Windows:
.venv\Scripts\activate

Then, it's ready to be used as a dedicated Python environment.

Install Required Packages

Ensure that pip is installed correctly. If pip is not included in your venv, install it manually:

wget https://bootstrap.pypa.io/get-pip.py
python3 get-pip.py

Then install all the required packages:

pip install -r requirements.txt

💻 Usage Examples

Use with Cursor Env

It's ready to be updated according to the more user-friendly Cursor environment.

Set the following in the MCP section of the Cursor settings:

uv --directory /path/to/prometheus_mcp_server run server.py

Use with an MCP Client (including Claude Desktop)

Configure the configuration file of your Claude Desktop application located at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)

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

Run the MCP Server Independently

Start this MCP server independently:

Using the uv Method

uv --directory /path/to/prometheus_mcp_server run server.py

This is also a way to ensure that this MCP server can start automatically, as Claude Desktop uses this ux script to start the server when the application launches.

Using the Regular Python Method

python3 server.py

🤝 Contribution

Contributions are welcome! Here's a quick guide:

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Add some AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).

📚 Documentation

For more information, please visit the project repository: https://github.com/yourusername/prometheus-mcp-server

This documentation introduces the features, installation, and usage of the Prometheus MCP server, as well as how to contribute to the project. We hope it's helpful to you!