# Prometheus MCP Server (oci · docker.io/prom/prometheus-mcp)

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

- Trust score: 41/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- oci · `docker.io/prom/prometheus-mcp`: 41/100 (this document), [markdown](https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp.md), [page](https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp)

## Channel facts

- Registry: `oci`
- Package: `docker.io/prom/prometheus-mcp`
- Version: `v0.19.0-rc.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-06.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3250 tokens (~83/item across 39 items; 30 tools + 9 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 85/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 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.
  - An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**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 docker.io/prom/prometheus-mcp:v0.19.0-rc.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add prometheus-prometheus-mcp -- docker run --rm -i docker.io/prom/prometheus-mcp:v0.19.0-rc.0
```

### Cursor

```json
{
  "mcpServers": {
    "prometheus-prometheus-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "prometheus-prometheus-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add prometheus-prometheus-mcp -- docker run --rm -i docker.io/prom/prometheus-mcp:v0.19.0-rc.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "prometheus-prometheus-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  prometheus-prometheus-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"]
```

### Netclaw

```json
{
  "McpServers": {
    "prometheus-prometheus-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "prometheus-prometheus-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/prom/prometheus-mcp:v0.19.0-rc.0"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 39)

First indexed and scored.

## MCP tools (30)

### `alertmanagers` (~18 tokens)

Get overview of Prometheus Alertmanager discovery

### `build_info` (~14 tokens)

Get Prometheus build information

### `clean_tombstones` (~44 tokens)

Removes the deleted data from disk and cleans up the existing tombstones. I/O- and CPU-intensive; prefer low-traffic periods and confirm with the user before calling.

### `config` (~12 tokens)

Get Prometheus configuration

### `delete_series` (~234 tokens)

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. Confirm the time range and matchers with the user before calling.

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `matches` (array, required): series selector arguments for series to delete,required
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.

### `docs_list` (~16 tokens)

List of Official Prometheus Documentation Files.

### `docs_read` (~40 tokens)

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

Input parameters:

- `file` (string, required): the name of the documentation file to read

### `docs_search` (~52 tokens)

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

Input parameters:

- `limit` (integer): maximum number of search results to return
- `query` (string, required): the query to search for in documentation

### `exemplar_query` (~234 tokens)

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

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `query` (string, required): the PromQL query to execute
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `flags` (~11 tokens)

Get runtime flags

### `healthy` (~20 tokens)

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

### `label_names` (~235 tokens)

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

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `matches` (array): series selector arguments to filter label names
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `label_values` (~247 tokens)

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

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `label` (string, required): the label to query values for,required
- `matches` (array): series selector arguments to filter label values
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `list_alerts` (~14 tokens)

List all active alerts

### `list_rules` (~19 tokens)

List all alerting and recording rules that are loaded

### `list_targets` (~16 tokens)

Get overview of Prometheus target discovery

### `metric_metadata` (~50 tokens)

Returns metadata about metrics currently scraped by the metric name.

Input parameters:

- `limit` (string): maximum number of metrics to return
- `metric` (string): metric name to retrieve metadata for, all metrics if empty

### `query` (~160 tokens)

Execute an instant query against the Prometheus datasource, returning one value per series at a single point in time

Input parameters:

- `query` (string, required): the PromQL query to execute
- `timestamp` (string): evaluation timestamp for the instant query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now e.g. 5m, 1h30m, etc. Defaults…
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `quit` (~34 tokens)

Management API endpoint that can be used to trigger a graceful shutdown of Prometheus. Only call this when the user explicitly requests a shutdown.

### `range_query` (~275 tokens)

Execute a range query against the Prometheus datasource, returning values over a time window; use for graphing and trend analysis

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `query` (string, required): the PromQL query to execute
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
- `step` (string): query resolution step width in Go duration format (e.g. '30s', '5m', '1h'), auto-set if unspecified
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `ready` (~31 tokens)

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

### `reload` (~34 tokens)

Management API endpoint that can be used to trigger a reload of the Prometheus configuration and rule files. Safe; applies changes without downtime.

### `runbooks_list` (~100 tokens)

List the runbooks embedded in this server: guided workflows (Agent Skills) for common Prometheus tasks - investigating error rates and alert spikes, finding top CPU/memory/disk consumers, troubleshooting missing metrics or empty query results, health-checking Prometheus, reducing high-cardinality metrics, reviewing and drafting recording and alerting rules, and tuning Prometheus configuration. Call this and read the matching runbook with runbooks_read before starting any of these tasks.

### `runbooks_read` (~91 tokens)

Read the named runbook: a guided workflow (Agent Skill) for a common Prometheus task, expressed in terms of this server's tools. Follow its guidance when a user request matches a runbook's purpose; runbooks_list shows what is available.

Input parameters:

- `name` (string, required): the skill name of the runbook to read, as returned by runbooks_list (e.g. investigate-error-rates)

### `runtime_info` (~14 tokens)

Get Prometheus runtime information

### `series` (~225 tokens)

Finds series by label matches

Input parameters:

- `end_time` (string): end timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to current t…
- `matches` (array, required): series selector arguments that select the series to return,required
- `start_time` (string): start timestamp for the query. Accepts: Unix epoch seconds, RFC3339, now, now-<duration>, now+<duration> (e.g. now-1h), or a duration string relative to now (e.g. 5m, 1h30m, etc). Defaults to 5m ago.
- `truncation_limit` (integer): truncation limit for query response in number of lines/entries; use lower limits (e.g. 50-100) for initial exploration, set to -1 to disable truncation

### `snapshot` (~61 tokens)

creates a snapshot of all current data into snapshots/<datetime>-<rand> under the TSDB's data directory and returns the directory as response. Safe, but confirm with the user before calling.

Input parameters:

- `skip_head` (boolean): skip data present in the head block

### `targets_metadata` (~67 tokens)

Returns metadata about metrics currently scraped by the target

Input parameters:

- `limit` (string): maximum number of targets to match
- `match_target` (string): label selectors to match targets, all targets if empty
- `metric` (string): metric name to retrieve metadata for, all metrics if empty

### `tsdb_stats` (~20 tokens)

Get usage and cardinality statistics from the TSDB

### `wal_replay_status` (~16 tokens)

Get current WAL replay status

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp#diagnostics

## Score history

- 2026-11-06: 41
- 2026-11-05: 40
- 2026-11-04: 40
- 2026-11-03: 39
- 2026-11-02: 39

## Common questions

### What is the Prometheus MCP Server server?

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

### Is the Prometheus MCP Server server safe to use?

Prometheus MCP Server scores 41 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 30 tools: alertmanagers, build_info, clean_tombstones, config, delete_series, and 25 more. Their descriptions and schemas cost roughly 2,404 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 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Prometheus MCP Server server?

VerifyMCP ran 12 checks on Prometheus MCP Server, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about Prometheus MCP Server: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Docker Hub: https://hub.docker.com/r/prom/prometheus-mcp
- Repository: https://github.com/prometheus/prometheus-mcp
- Changelog RSS feed: https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp.json
- HTML version of this page: https://verifymcp.io/servers/prometheus-prometheus-mcp/docker-io-prom-prometheus-mcp