Prometheus MCP Server
About
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
Details
- Author
- pab1it0
- GitHub stars
- 492
- Downloads
- 778
- Categories
- Cloud Service, Infrastructure, Other, Developer Tools, AI
Jump to
- Execute instant and range PromQL queries against Prometheus
- Discover and explore metrics with pagination and filtering
- Get metadata for metrics and search by name or description
- View scrape target information
- Support for basic auth, bearer token, and mutual TLS authentication
- Configurable transport modes (stdio, HTTP, SSE)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Prometheus MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install and run the server via Docker, or deploy to Kubernetes using the provided Helm chart. Configure it by setting the PROMETHEUS_URL environment variable to point to your Prometheus server, plus optional authentication and transport variables. Add the server to your MCP client’s configuration (for example, Claude Desktop or VS Code) using the Docker command shown in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"prometheus mcp server": {
"prometheus-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"\\"
]
}
}
}
}
McpServers
{
"prometheus-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"\\"
]
}
}
Prometheus MCP Server
Give AI assistants the power to query your Prometheus metrics.
A [Model Context Protocol][mcp] (MCP) server that provides access to your Prometheus metrics and queries through standardized MCP interfaces, allowing AI assistants to execute PromQL queries and analyze your metrics data.
[mcp]: https://modelcontextprotocol.io
Getting Started
Prerequisites
- Prometheus server accessible from your environment
- MCP-compatible client (Claude Desktop, VS Code, Cursor, Windsurf, etc.)
Installation Methods
<details>
<summary><b>Claude Desktop</b></summary>
Add to your Claude Desktop configuration:
{
"mcpServers": {
"prometheus": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PROMETHEUS_URL",
"ghcr.io/pab1it0/prometheus-mcp-server:latest"
],
"env": {
"PROMETHEUS_URL": "<your-prometheus-url>"
}
}
}
}
</details>
<details>
<summary><b>Claude Code</b></summary>
Install via the Claude Code CLI:
claude mcp add prometheus --env PROMETHEUS_URL=http://your-prometheus:9090 -- docker run -i --rm -e PROMETHEUS_URL ghcr.io/pab1it0/prometheus-mcp-server:latest
</details>
<details>
<summary><b>VS Code / Cursor / Windsurf</b></summary>
Add to your MCP settings in the respective IDE:
{
"prometheus": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PROMETHEUS_URL",
"ghcr.io/pab1it0/prometheus-mcp-server:latest"
],
"env": {
"PROMETHEUS_URL": "<your-prometheus-url>"
}
}
}
</details>
<details>
<summary><b>Docker Desktop</b></summary>
The easiest way to run the Prometheus MCP server is through Docker Desktop:
<a href="https://hub.docker.com/open-desktop?url=https://open.docker.com/dashboard/mcp/servers/id/prometheus/config?enable=true">
</a>
1. Via MCP Catalog: Visit the Prometheus MCP Server on Docker Hub and click the button above
2. Via MCP Toolkit: Use Docker Desktop's MCP Toolkit extension to discover and install the server
3. Configure your connection using environment variables (see Configuration Options below)
</details>
<details>
<summary><b>Manual Docker Setup</b></summary>
Run directly with Docker:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




