A side-by-side look at the Observability MCP and Prometheus MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Observability MCP for monitoring work as a local process; choose Prometheus MCP Server for monitoring. You can also run both side by side in one mcpServers block.
list_sources, list_services, query_metrics.alertmanagers, build_info, config.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Monitoring | Monitoring |
| Quality signal | 59/100 · Good | 53/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 7 | 121 |
| Directory activity | 2 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 8 | 30 |
| Full listing | View Observability MCP | View Prometheus MCP Server |
list_sourcesDiscover configured backends and connection statuslist_servicesDiscover monitored services across all backendsquery_metricsQuery metrics with pre-computed summary statsquery_logsQuery logs with error/warning counts and top patternsget_service_healthHealth score combining metrics + logs (0–100)detect_anomaliesCross-signal anomaly detection with robust (median/MAD + trend) analysisget_topologyReturn the merged infrastructure graph (resources + edges) from every topology-capable connector, filterable by source/kind/scopeget_blast_radiusPivot on the universal `RUNS_ON` relation — "if this resource's host fails, who else fails?". Works for pod→node, vm→hypervisor, container→hostalertmanagersGet overview of Prometheus Alertmanager discoverybuild_infoGet Prometheus build informationconfigGet Prometheus configurationdocs_listList of Official Prometheus Documentation Filesdocs_readRead the named markdown file containing official Prometheus documentation from the prometheus/docs repodocs_searchSearch the markdown files containing official Prometheus documentation from the prometheus/docs repoexemplar_queryPerforms a query for exemplars by the given query and time rangeflagsGet runtime flagshealthyManagement API endpoint that can be used to check Prometheus healthlabel_namesReturns the unique label names present in the block in sorted order by given time range and matcherslabel_valuesPerforms a query for the values of the given label, time range and matcherslist_alertsList all active alertsPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"observability-mcp": {
"command": "npx",
"args": [
"-y",
"@thotischner/observability-mcp"
]
}
}
}
No confirmed install command for Prometheus MCP Server yet — follow the setup steps linked from its listing page rather than a guessed package name.