prometheus-mcp-server MCP — Use Cases, Install & Live Demo

Why use it

Key features

6 focused tools over the Prometheus API
PromQL instant + range queries with custom intervals
Metric discovery and metadata for agents that don't know your label space
Auth options: basic, bearer, mTLS, custom headers

Live Demo

What it looks like in practice

prometheus.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "prometheus": {
      "command": "uvx",
      "args": [
        "prometheus-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "prometheus": {
      "command": "uvx",
      "args": [
        "prometheus-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "prometheus": {
      "command": "uvx",
      "args": [
        "prometheus-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "prometheus": {
      "command": "uvx",
      "args": [
        "prometheus-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "prometheus",
      "command": "uvx",
      "args": [
        "prometheus-mcp-server"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "prometheus": {
      "command": {
        "path": "uvx",
        "args": [
          "prometheus-mcp-server"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add prometheus -- uvx prometheus-mcp-server

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use prometheus-mcp-server

How to diagnose a latency spike with Prometheus + Claude

👤 On-call SREs ⏱ ~10 min intermediate

When to use: A service p99 alert fires — you need context without memorizing PromQL.

Prerequisites

Prometheus URL reachable — Set PROMETHEUS_URL in the MCP config; add auth if protected

Flow

Scope the spike

Query http request p99 latency for service X in the last hour, 30-second resolution. Compare to the last 7 days baseline.✓ Copied

→ Range query result showing the spike
Find correlated metrics

For the spike window, what other metrics for service X moved >2 sigma? CPU, memory, GC, queue depth?✓ Copied

→ Candidate culprit metrics
Narrow by label

Break down the spike by pod/host labels. Is it one pod or fleet-wide?✓ Copied

→ Per-label decomposition

Outcome: A hypothesis tied to specific metrics in under 5 minutes.

Pitfalls

Query returns no data — Check label names with list_metrics — label casing and delimiters vary between exporters

Combine with: kubectl

Generate a weekly SLO compliance report from Prometheus

👤 SRE leads ⏱ ~25 min intermediate

When to use: Friday SLO review — you want numbers not vibes.

Flow

Define the SLIs

For service X, compute this week's availability (success/total ratio) and latency (requests under threshold / total) as numbers.✓ Copied

→ Two ratios with burn rate
Compare to SLO

Availability SLO = 99.9%, latency SLO = 95%. Am I above or below? Project error budget exhaustion.✓ Copied

→ Verdict + days of budget remaining

Outcome: Defensible SLO report with numbers not 'mostly fine'.

Combine with: google-sheets

Audit Prometheus scrape target health with Claude

👤 Platform engineers ⏱ ~15 min intermediate

When to use: You suspect half your targets are down but haven't checked.

Flow

Get targets

Call get_targets. Group by job; which have any DOWN instances?✓ Copied

→ Table of job → up/down counts
Investigate

For the worst offender, show the lastError for the DOWN instances. Likely cause?✓ Copied

→ Actionable cause per target

Outcome: Rescued scrapes in minutes.

Combinations

Pair with other MCPs for X10 leverage

prometheus + kubectl

Pair metric anomalies with pod state

For the service with the latency spike, correlate Prometheus data with kubectl describe on its pods.✓ Copied

prometheus + sentry

Metric spike + error spike correlation

Sentry shows errors doubled at 14:00 — what Prometheus metrics moved at the same time?✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
health_check		Verify connectivity	1 API call
execute_query	query: promql, time?	Instant snapshot	1 query
execute_range_query	query, start, end, step	Time-series analysis	1 query (may be expensive)
list_metrics	match?: str	Discovery when you don't know the metric name	1 API call
get_metric_metadata	metric: str	Understand units before computing	1 API call
get_targets		Scrape health	1 API call

Cost & Limits

What this costs to run

API quota: Prometheus scales with your server; expensive queries can stress it
Tokens per call: Range queries with many series can hit 10k+ tokens
Monetary: Free
Tip: Use step wisely on range queries; 10s resolution over 24h is 8640 samples per series

Security

Permissions, secrets, blast radius

Minimum scopes: read-only access to Prometheus API

Credential storage: Bearer token or basic auth in env; mTLS cert paths if used

Data egress: Your Prometheus URL only

Troubleshooting

Common errors and fixes

Query returns empty with no error

Metric/label name doesn't exist. Use list_metrics with a match prefix to verify

Range query times out

Reduce time range or increase step. Prometheus query engine has per-query resource limits

401 with bearer token

Token lacks read permission on /api/v1; check reverse proxy if Prometheus is behind one

Verify: curl -H 'Authorization: Bearer $T' $PROMETHEUS_URL/api/v1/status/config

Alternatives

prometheus-mcp-server vs others

Alternative	When to use it instead	Tradeoff
Grafana MCP	You already visualize in Grafana and want dashboard/alert ops	Heavier; more features than you may need
Datadog MCP	Datadog is your metrics store	Paid; different query language

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills