Prometheus MCP Server
Wraps the entire Prometheus HTTP API for metrics querying, alerting, configuration management, and TSDB operations. You get instant queries, range queries, series lookups, label exploration, metadata inspection, alert and rule management, plus target discovery details all through MCP tools. It includes optional TSDB admin endpoints for deleting series and creating snapshots if you explicitly enable them with a flag. The server also bundles Prometheus documentation search so your LLM can reference best practices on metric naming or query syntax. Built in Go, supports TOON encoding for token efficiency, and lets you truncate API responses to control context size. Ideal when you need an LLM to investigate slow queries, analyze high cardinality metrics, suggest recording rules, or generate PromQL on the fly.
- GitHub stars
- 48
- tools
- 30
- transport
- STDIO
- last updated
- Apr 25, 2026
Tools
30 toolsPublic tool metadata for what this MCP can expose to an agent.
alertmanagersGet overview of Prometheus Alertmanager discovery
Get overview of Prometheus Alertmanager discovery
No parameter schema in public metadata yet.
build_infoGet Prometheus build information
Get Prometheus build information
No parameter schema in public metadata yet.
configGet Prometheus configuration
Get Prometheus configuration
No parameter schema in public metadata yet.
docs_listList of Official Prometheus Documentation Files
List of Official Prometheus Documentation Files
No parameter schema in public metadata yet.
docs_readRead the named markdown file containing official Prometheus documentation from the prometheus/docs repo
Read the named markdown file containing official Prometheus documentation from the prometheus/docs repo
No parameter schema in public metadata yet.
docs_searchSearch the markdown files containing official Prometheus documentation from the prometheus/docs repo
Search the markdown files containing official Prometheus documentation from the prometheus/docs repo
No parameter schema in public metadata yet.
exemplar_queryPerforms a query for exemplars by the given query and time range
Performs a query for exemplars by the given query and time range
No parameter schema in public metadata yet.
flagsGet runtime flags
Get runtime flags
No parameter schema in public metadata yet.
healthyManagement API endpoint that can be used to check Prometheus health
Management API endpoint that can be used to check Prometheus health
No parameter schema in public metadata yet.
label_namesReturns the unique label names present in the block in sorted order by given time range and matchers
Returns the unique label names present in the block in sorted order by given time range and matchers
No parameter schema in public metadata yet.
label_valuesPerforms a query for the values of the given label, time range and matchers
Performs a query for the values of the given label, time range and matchers
No parameter schema in public metadata yet.
list_alertsList all active alerts
List all active alerts
No parameter schema in public metadata yet.
list_rulesList all alerting and recording rules that are loaded
List all alerting and recording rules that are loaded
No parameter schema in public metadata yet.
list_targetsGet overview of Prometheus target discovery
Get overview of Prometheus target discovery
No parameter schema in public metadata yet.
metric_metadataReturns metadata about metrics currently scraped by the metric name
Returns metadata about metrics currently scraped by the metric name
No parameter schema in public metadata yet.
queryExecute an instant query against the Prometheus datasource, returning one value per series at a single point in time
Execute an instant query against the Prometheus datasource, returning one value per series at a single point in time
No parameter schema in public metadata yet.
quitManagement API endpoint that can be used to trigger a graceful shutdown of Prometheus
Management API endpoint that can be used to trigger a graceful shutdown of Prometheus
No parameter schema in public metadata yet.
range_queryExecute a range query against the Prometheus datasource, returning values over a time window
Execute a range query against the Prometheus datasource, returning values over a time window
No parameter schema in public metadata yet.
readyManagement API endpoint that can be used to check Prometheus is ready to serve traffic (i.e. respond to queries
Management API endpoint that can be used to check Prometheus is ready to serve traffic (i.e. respond to queries
No parameter schema in public metadata yet.
reloadManagement API endpoint that can be used to trigger a reload of the Prometheus configuration and rule files
Management API endpoint that can be used to trigger a reload of the Prometheus configuration and rule files
No parameter schema in public metadata yet.
runbooks_listList the runbooks embedded in this server: guided workflows (Agent Skills) for common Prometheus tasks
List the runbooks embedded in this server: guided workflows (Agent Skills) for common Prometheus tasks
No parameter schema in public metadata yet.
runbooks_readRead the named runbook by skill name (e.g. `check-system-health`)
Read the named runbook by skill name (e.g. `check-system-health`)
No parameter schema in public metadata yet.
runtime_infoGet Prometheus runtime information
Get Prometheus runtime information
No parameter schema in public metadata yet.
seriesFinds series by label matchers
Finds series by label matchers
No parameter schema in public metadata yet.
targets_metadataReturns metadata about metrics currently scraped by the target
Returns metadata about metrics currently scraped by the target
No parameter schema in public metadata yet.
tsdb_statsGet usage and cardinality statistics from the TSDB
Get usage and cardinality statistics from the TSDB
No parameter schema in public metadata yet.
wal_replay_statusGet current WAL replay status
Get current WAL replay status
No parameter schema in public metadata yet.
clean_tombstonesRemoves the deleted data from disk and cleans up the existing tombstones
Removes the deleted data from disk and cleans up the existing tombstones
No parameter schema in public metadata yet.
delete_seriesdeletes data for a selection of series in a time range
deletes data for a selection of series in a time range
No parameter schema in public metadata yet.
snapshotcreates a snapshot of all current data into snapshots/<datetime>-<rand> under the TSDB's data directory and returns the directory as response
creates a snapshot of all current data into snapshots/<datetime>-<rand> under the TSDB's data directory and returns the directory as response
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Prometheus MCP Server
Prometheus MCP Server Logo
About
This is an MCP server to allow LLMs to interact with a running Prometheus instance via the API to do things like generate and execute promql queries, list and analyze metrics, etc.
Demos and Examples
Asking Claude to Investigate Slow Queries
The prompt used was:
querying my metrics is slow, can you help me figure out why?
Details
- Repository
- github.com/tjhop/prometheus-mcp-server
- Website
- github.com/tjhop/prometheus-mcp-server
- Category
- Monitoring & Observability
- Package
ghcr.io/tjhop/prometheus-mcp-server:0.18.0- Transport
- STDIO
- Registry
- MCP registry, active
Related Monitoring & Observability MCP servers
View all
Agent Analyticsagent-analytics/agent-analytics-mcpAnalytics your AI agent can actually use. Track, experiment, and optimize via MCP.0stars
Gitignore Drift Monitordailyaiagents-cpu/dailyai-osWatcher — count uncommitted files in repo, surface dominant drift class. YELLOW >100, RED >250.0stars
Trace Forgemdfifty50-boop/trace-forge-mcpStructured execution trace and span logging for AI agents0stars
Hive Sla Monitorsrotzin/hive-mcp-sla-monitorService level agreement monitoring for the Hive agent fleet0stars
Ndjson Local Log Triage Mcpvola-trebla/ndjson-local-log-triage-mcpStreams NDJSON log triage: query patterns, detect anomalies, summarize timelines without full load.0stars
MCP Server for Uptime Kumadavidfuchs/mcp-uptime-kumaManage your Uptime Kuma 2 instance from an LLM: monitors, status pages, notifications, maintenance70stars