io.github.tjhop/prometheus-mcp-server
Prometheus MCP Server
Is the Prometheus MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-01.
An API-complete MCP server to manage Prometheus-compatible backends.
alive probed 2026-11-14 · unchanged since 2026-11-01
28tools
4.2ktokens in Claude Opus 5.5
2.1 %of Claude's 200k window
1.7×the median server
2.3 sto initialize
11 msto list tools
- Run it
- docker run -i --rm ghcr.io/tjhop/prometheus-mcp-server:0.18.0 (stdio, probed in a container with the network off)
- Host
- ghcr.io
- Reports itself as
- prometheus-mcp-server (version=0.18.0, build_date=2026-04-25T05:01:51Z, commit=924e43dbea816b92c3e79e73c1568af417e8e30e, docs_commit=37db7273b5471dae8343e92ba117069c2ccc95c3)
- Capabilities
- logging, resources, tools
- Instructions
- 18 297 characters
- Of a 1M window
- 0.4 % of a 1M context window
- Count
- 4.2k tokens in Claude Opus 5.5, exact, measured 2026-11-01. With the Claude Code prefix mcp__…__ on each tool name: 4.6k. The o200k_base estimate is 2.4k. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/tjhop/prometheus-mcp-server
- Website
- https://github.com/tjhop/prometheus-mcp-server
- Registry
- active, updated 2026-04-25 · registry entry
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.76×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| range_query | 418 | 238 | 10 % |
| label_values | 415 | 236 | 10 % |
| delete_series | 383 | 218 | 9 % |
| label_names | 378 | 215 | 9 % |
| series | 371 | 211 | 9 % |
Compare this server with others.
More servers
Other registry entries on ghcr.io, the ones next to this name; all of them.
- io.github.tidynest/raven-nest-mcp · alive
- Tiger MCP io.github.timescale/tiger-cli · alive
- anodizer io.github.tj-smith47/anodizer · crashed on start
- io.github.tj-smith47/cfgd · crashed on start
- SQL Sentinel MCP Server io.github.tkmawarire/sql-sentinel · crashed on start
- Telegram MCP Server io.github.tolboy/telegram-mcp-tdlib · needs env
- Portage io.github.tomtom87/portage · alive
- Portage Store io.github.tomtom87/portage-ucp · alive
Servers that mention prometheus.
- ai.getvda/kafka-and-postgres-monitoring-stack · newer protocol
- ai.getvda/postgres-kafka-prometheus-stack-generator · newer protocol
- ai.getvda/postgres-prometheus-stack-generator · newer protocol
- io.github.PrometheusAgency/bluesky-brand-monitor · needs auth
- io.github.PrometheusAgency/bluesky-followers-export · needs auth
- io.github.PrometheusAgency/bluesky-scraper · needs auth
- io.github.PrometheusAgency/eu-industrial-emissions · needs auth
- io.github.PrometheusAgency/eudr-parcel-screener · needs auth
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers initialize and tools/list. Nothing to fix.