Grafana Tempo MCP Server vs Prometheus MCP Server

A side-by-side comparison of two Monitoring & Observability servers — tools, transport, auth, maintenance, and copy-paste config for each.

	Grafana Tempo MCP Server Query distributed traces in Grafana Tempo with TraceQL (archived; Tempo now has embedded MCP). Unverified stdio (local) No auth Go	Prometheus MCP Server Run PromQL queries and analyze Prometheus metrics from any MCP client. Verified stdio (local) No auth Python
Category	Monitoring & Observability	Monitoring & Observability
Language	Go	Python
Transport	stdio (local)	stdio (local)
Auth	None	None
GitHub stars	90	340
Last commit	2 months ago	1 month ago
Verified
Actively maintained
Install	`docker run -i --rm -e TEMPO_URL grafana/tempo-mcp-server`	`uvx prometheus-mcp-server`
Repo	Open	Open

Verdict

Pick Grafana Tempo MCP Server if you prefer its approach (query distributed traces in grafana tempo with traceql (archived; tempo now has embedded mcp)).

Pick Prometheus MCP Server if you prefer the more popular, battle-tested option, and you need the broadest set of tools.

Add Grafana Tempo MCP Server

Install / run

docker run -i --rm -e TEMPO_URL grafana/tempo-mcp-server

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "grafana-tempo-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "TEMPO_URL",
        "grafana/tempo-mcp-server"
      ],
      "env": {
        "TEMPO_URL": "<your-tempo-query-endpoint>"
      }
    }
  }
}

Requires Docker to be installed and running.

Add Prometheus MCP Server

Install / run

uvx prometheus-mcp-server

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "prometheus-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PROMETHEUS_URL",
        "ghcr.io/pab1it0/prometheus-mcp-server:latest"
      ],
      "env": {
        "PROMETHEUS_URL": "<your-prometheus-url>"
      }
    }
  }
}

Requires Docker to be installed and running.

FAQ

Grafana Tempo MCP Server or Prometheus MCP Server — which is better?

Pick Grafana Tempo MCP Server if you prefer its approach (query distributed traces in grafana tempo with traceql (archived; tempo now has embedded mcp)). Pick Prometheus MCP Server if you prefer the more popular, battle-tested option, and you need the broadest set of tools.

Can I use both Grafana Tempo MCP Server and Prometheus MCP Server?

Yes — MCP clients let you enable multiple servers at once. Add both configs to your client's mcpServers and use whichever tool fits the task.

Do Grafana Tempo MCP Server and Prometheus MCP Server work with Claude, Cursor and Windsurf?

Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.

View Grafana Tempo MCP Server →View Prometheus MCP Server →More comparisons →