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

Prometheus MCP Server

OCI · GHCR.IO/TJHOP/PROMETHEUS-MCP-SERVER:0.18.0 · SCANNED SEP 20

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

0 this week 48 Trust /100
Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency23
Schema Quality & AI Usability75
  • 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 Management93
  • Stability observed for 28 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
Tool Safety85
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 2 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "exemplar_query" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it.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

How do I install the Prometheus MCP Server server?

Prometheus MCP Server runs locally as a container image, launched with docker run --rm -i ghcr.io/tjhop/prometheus-mcp-server:0.18.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

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
// .cursor/mcp.json
{
  "mcpServers": {
    "tjhop-prometheus-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/tjhop/prometheus-mcp-server:0.18.0"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "tjhop-prometheus-mcp-server": {
      "command": "docker",
      "args": [
        "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"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "tjhop-prometheus-mcp-server": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "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.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 9 Sept 26 0
    • Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed oci/ghcr.io/tjhop/prometheus-mcp-server:0.18.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

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.

Common questions

What is the Prometheus MCP Server server?

Prometheus MCP Server is listed in the public MCP registry as io.github.tjhop/prometheus-mcp-server. An API-complete MCP server to manage Prometheus-compatible backends. This page covers its container image (ghcr.io/tjhop/prometheus-mcp-server:0.18.0).

Is the Prometheus MCP Server server safe to use?

Prometheus MCP Server scores 48 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Prometheus MCP Server server expose?

Prometheus MCP Server exposes 28 tools: alertmanagers, build_info, clean_tombstones, config, delete_series, and 23 more. Their descriptions and schemas cost roughly 1,764 tokens of context every time the server is loaded.

Is the Prometheus MCP Server server still maintained?

Prometheus MCP Server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Prometheus MCP Server server under?

Prometheus MCP Server declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.