Prometheus MCP Server by prometheus: safety score
C 56 Provisional Not reviewed Not tested
Prometheus MCP Server by prometheus is a vendor MCP server for Prometheus with 15 read, 1 write and 5 destructive tools. It does not have a read-only mode and needs to run locally; its provisional OpsMCP grade is C (56%), last checked 16 Oct 2026.
An API-complete MCP server to manage Prometheus-compatible backends.
Tool capability partly scored. Access partly scored. Maintenance partly scored. 1 of 4 factors scored.
Can it change or delete things?
Yes. The extracted tools include at least one destructive tool, so it can change or delete things.
| Tool | Class |
|---|---|
alertmanagers Get overview of Prometheus Alertmanager discovery
from the description (get) | Read |
build_info Get Prometheus build information
from the description (get) | Read |
clean_tombstones 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.
from the description (removes) | Destructive |
config Get Prometheus configuration
from the description (get) | Read |
delete_series 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 wit...
from the name (delete) | Destructive |
docs_list List of Official Prometheus Documentation Files.
from the name (list) | Read |
docs_read annotation disagrees Read the named markdown file containing official Prometheus documentation from the prometheus/docs repo
from the name | Unknown |
docs_search Search the markdown files containing official Prometheus documentation from the prometheus/docs repo
from the name (search) | Read |
exemplar_query annotation disagrees Execute an exemplar query against the Prometheus datasource to find trace exemplars associated with metric samples
from the description (execute) | Destructive |
flags Get runtime flags
from the description (get) | Read |
healthy annotation disagrees Management API endpoint that can be used to check Prometheus health.
from the name | Unknown |
label_names annotation disagrees Returns the unique label names present in the block in sorted order by given time range and matches
from the name | Unknown |
label_values annotation disagrees Performs a query for the values of the given label, time range and matches
from the name | Unknown |
list_alerts List all active alerts
from the name (list) | Read |
list_rules List all alerting and recording rules that are loaded
from the name (list) | Read |
list_stores List all store API servers
from the name (list) | Read |
list_targets Get overview of Prometheus target discovery
from the name (list) | Read |
metric_metadata annotation disagrees Returns metadata about metrics currently scraped by the metric name.
from the name | Unknown |
query annotation disagrees Execute an instant query against the Prometheus datasource, returning one value per series at a single point in time
from the description (execute) | Destructive |
quit Management API endpoint that can be used to trigger a graceful shutdown of Prometheus. Only call this when the user explicitly requests a shutdown.
from the name | Unknown |
range_query annotation disagrees Execute a range query against the Prometheus datasource, returning values over a time window; use for graphing and trend analysis
from the description (execute) | Destructive |
ready annotation disagrees Management API endpoint that can be used to check Prometheus is ready to serve traffic (i.e. respond to queries.)
from the name | Unknown |
reload Management API endpoint that can be used to trigger a reload of the Prometheus configuration and rule files. Safe; applies changes without downtime.
from the name | Unknown |
runbooks_list 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, reduc...
from the name (list) | Read |
runbooks_read 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.
from the description (list) | Read |
runtime_info Get Prometheus runtime information
from the description (get) | Read |
series annotation disagrees Finds series by label matches
from the name | Unknown |
snapshot 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.
from the description (creates) | Write |
targets_metadata annotation disagrees Returns metadata about metrics currently scraped by the target
from the name | Unknown |
tsdb_stats Get usage and cardinality statistics from the TSDB
from the description (get) | Read |
wal_replay_status Get current WAL replay status
from the description (get) | Read |
Score
56 of 100 points (56%). A factor that was not scored counts as 0 of its full weight.
| Factor | Points | Full weight | Status |
|---|---|---|---|
| Tool capability | 18 | 35 | Partly scored |
| Access | 6 | 25 | Partly scored |
| Maintenance | 12 | 20 | Partly scored |
| Publisher | 20 | 20 | Scored |
Tool capability
15 read, 1 write, 5 destructive, 10 unknown.
Access
| Part | Value | Points | Where this came from |
|---|---|---|---|
| Scope | unknown | unknown | unknown |
| Where it runs | Local process | 6 of 8 | Registry package transport is stdio. |
| Credentials | unknown | unknown | unknown |
Maintenance
| Part | Value | Points |
|---|---|---|
| Last commit | 0 days | 8 of 8 |
| Releases | 173 days | 4 of 6 |
| Issues | unknown | unknown |
Publisher
| Part | Value | Points | Where this came from |
|---|---|---|---|
| Who publishes it | Official vendor | 8 of 8 | GitHub owner 'prometheus' is on the vendor allowlist (Prometheus). |
| Registry listing | Listed | 5 of 5 | Official registry server io.github.tjhop/prometheus-mcp-server (status active). |
| License | Apache-2.0 | 4 of 4 | GitHub SPDX license Apache-2.0. |
| Stars | 125 | 2 of 2 | 125 GitHub stars. |
| Repository age | 532 days | 1 of 1 | Repository created 2025-05-02T03:17:53Z. |
What this score does not cover
This score is not a code audit and it is not a human review. It has not been hands-on tested. Nothing on this page is a certification.
Access needed
Environment variables: unknown. The registry entry does not list any.
Maintenance
- Archived
- no
- Last commit
- 16 Oct 2026 · 3c32125
- Latest release
- v0.18.0 · 25 Apr 2026
- Issues
- unknown
- Stars
- 125
- License
- Apache-2.0
- Repository created
- 2 May 2025
npm and PyPI
- npm
- No npm package in the registry entry.
- PyPI
- No PyPI package in the registry entry.
- Maintainers
- unknown
Install
docker run ghcr.io/tjhop/prometheus-mcp-server:0.18.0Other Prometheus servers
Badge
Sources for this listing
registry:prometheus