Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Prometheus MCP Server

OCI · GHCR.IO/TJHOP/PROMETHEUS-MCP-SERVER:0.18.0 · SCANNED AUG 3

An API-complete MCP server to manage Prometheus-compatible backends.

−1 this week 37 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • CVE data not yet available for this package.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency-health data not yet available.Unverified
Provenance & Transparency19
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 5214 tokens (~179/item across 29 items; 28 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

oci · ghcr.io/tjhop/prometheus-mcp-server:0.18.0

# add to Claude Code
claude mcp add tjhop-prometheus-mcp-server -- docker run --rm -i ghcr.io/tjhop/prometheus-mcp-server:0.18.0
# add to Codex CLI
codex mcp add tjhop-prometheus-mcp-server -- docker run --rm -i ghcr.io/tjhop/prometheus-mcp-server:0.18.0
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tjhop-prometheus-mcp-server": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/tjhop/prometheus-mcp-server:0.18.0"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  tjhop-prometheus-mcp-server:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/tjhop/prometheus-mcp-server:0.18.0"]
// mcp.json
{
  "mcpServers": {
    "tjhop-prometheus-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/tjhop/prometheus-mcp-server:0.18.0"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +3
    • Stability: unverified → 0.23 functional
  • 31 Jul 26 −4
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 +33
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 100 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: good functional
  • 26 Jul 26 5

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed oci/ghcr.io/tjhop/prometheus-mcp-server:0.18.0

Provenance none

Ecosystem: oci · Outcome: none

Reason: no_attestation

MCP tools — 28 exposed · ~1,764 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
alertmanagers ~18

Get overview of Prometheus Alertmanager discovery

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

build_info ~14

Get Prometheus build information

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

clean_tombstones ~24

Removes the deleted data from disk and cleans up the existing tombstones

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

config ~12

Get Prometheus configuration

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

delete_series ~181

Deletes data for a selection of series in a time range. Both start_time and end_time are required to prevent accidental deletion of all data. Deletion creates tombstones; run clean_tombstones or wait for compaction to reclaim disk space.

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
matchesnull|arrayyesseries selector arguments for series to delete,required
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.

No output schema declared.

No examples provided.

docs_list ~16

List of Official Prometheus Documentation Files.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

docs_read ~40

Read the named markdown file containing official Prometheus documentation from the prometheus/docs repo

NameTypeReqDescription
filestringyesthe name of the documentation file to read

No output schema declared.

No examples provided.

docs_search ~52

Search the markdown files containing official Prometheus documentation from the prometheus/docs repo

NameTypeReqDescription
limitintegermaximum number of search results to return
querystringyesthe query to search for in documentation

No output schema declared.

No examples provided.

exemplar_query ~176

Execute an exemplar query against the Prometheus datasource to find trace exemplars associated with metric samples

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
querystringyesthe PromQL query to execute
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

flags ~11

Get runtime flags

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

healthy ~20

Management API endpoint that can be used to check Prometheus health.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

label_names ~179

Returns the unique label names present in the block in sorted order by given time range and matches

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
matchesnull|arrayseries selector arguments to filter label names
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

label_values ~191

Performs a query for the values of the given label, time range and matches

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
labelstringyesthe label to query values for,required
matchesnull|arrayseries selector arguments to filter label values
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

list_alerts ~14

List all active alerts

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_rules ~19

List all alerting and recording rules that are loaded

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_targets ~16

Get overview of Prometheus target discovery

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

metric_metadata ~50

Returns metadata about metrics currently scraped by the metric name.

NameTypeReqDescription
limitstringmaximum number of metrics to return
metricstringmetric name to retrieve metadata for, all metrics if empty

No output schema declared.

No examples provided.

query ~111

Execute an instant query against the Prometheus datasource

NameTypeReqDescription
querystringyesthe PromQL query to execute
timestampstringevaluation timestamp for the instant query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now e.g. 5m, 1h30m, etc. Defaults to current time.
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

quit ~23

Management API endpoint that can be used to trigger a graceful shutdown of Prometheus.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

range_query ~202

Execute a range query against the Prometheus datasource

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
querystringyesthe PromQL query to execute
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
stepstringquery resolution step width in Go duration format (e.g. '30s', '5m', '1h'), auto-set if unspecified
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

ready ~31

Management API endpoint that can be used to check Prometheus is ready to serve traffic (i.e. respond to queries.)

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

reload ~27

Management API endpoint that can be used to trigger a reload of the Prometheus configuration and rule files.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

runtime_info ~14

Get Prometheus runtime information

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

series ~169

Finds series by label matches

NameTypeReqDescription
end_timestringend timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current time.
matchesnull|arrayyesseries selector arguments that select the series to return,required
start_timestringstart timestamp for the query. Accepts: Unix epoch seconds, RFC3339, or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
truncation_limitintegertruncation limit for query response in number of lines/entries, set to -1 to disable truncation

No output schema declared.

No examples provided.

snapshot ~51

creates a snapshot of all current data into snapshots/<datetime>-<rand> under the TSDB's data directory and returns the directory as response.

NameTypeReqDescription
skip_headbooleanskip data present in the head block

No output schema declared.

No examples provided.

targets_metadata ~67

Returns metadata about metrics currently scraped by the target

NameTypeReqDescription
limitstringmaximum number of targets to match
match_targetstringlabel selectors to match targets, all targets if empty
metricstringmetric name to retrieve metadata for, all metrics if empty

No output schema declared.

No examples provided.

tsdb_stats ~20

Get usage and cardinality statistics from the TSDB

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

wal_replay_status ~16

Get current WAL replay status

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.