A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
{
"mcpServers": {
"prometheus": {
"env": {
"PROMETHEUS_URL": "<your-prometheus-url>"
},
"args": [
"run",
"-i",
"--rm",
"-e",
"PROMETHEUS_URL",
"ghcr.io/pab1it0/prometheus-mcp-server:latest"
],
"command": "docker"
}
}
}A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 2 days ago. 406 stars.
Will it work with my client?
Transport: stdio, sse, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Context cost
6 tools. ~400 tokens (0.2% of 200K).
No automated test available for this server. Check the GitHub README for setup instructions.
health_checkHealth check endpoint for container monitoring and status verification
execute_queryExecute a PromQL instant query against Prometheus
execute_range_queryExecute a PromQL range query with start time, end time, and step interval
list_metricsList all available metrics in Prometheus with pagination and filtering support
get_metric_metadataGet metadata for one metric or bulk metadata with optional filtering
get_targetsGet information about all scrape targets
This server is missing a description.If you've used it, help the community.
Add informationLast scanned 2h ago
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.