prometheus-mcp-server MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

prometheus.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : prometheus-mcp-server

How to diagnose a latency spike with Prometheus + Claude

👤 On-call SREs ⏱ ~10 min intermediate

Quand l'utiliser : A service p99 alert fires — you need context without memorizing PromQL.

Prérequis

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

Déroulement

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.✓ Copié

→ 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?✓ Copié

→ Candidate culprit metrics
Narrow by label

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

→ Per-label decomposition

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

Pièges

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

Combiner avec : kubectl

Generate a weekly SLO compliance report from Prometheus

👤 SRE leads ⏱ ~25 min intermediate

Quand l'utiliser : Friday SLO review — you want numbers not vibes.

Déroulement

Define the SLIs

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

→ Two ratios with burn rate
Compare to SLO

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

→ Verdict + days of budget remaining

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

Combiner avec : google-sheets

Audit Prometheus scrape target health with Claude

👤 Platform engineers ⏱ ~15 min intermediate

Quand l'utiliser : You suspect half your targets are down but haven't checked.

Déroulement

Get targets

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

→ Table of job → up/down counts
Investigate

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

→ Actionable cause per target

Résultat : Rescued scrapes in minutes.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

prometheus + kubectl

Pair metric anomalies with pod state

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

prometheus + sentry

Metric spike + error spike correlation

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: Prometheus scales with your server; expensive queries can stress it
Tokens par appel: Range queries with many series can hit 10k+ tokens
Monétaire: Free
Astuce: Use step wisely on range queries; 10s resolution over 24h is 8640 samples per series

Sécurité

Permissions, secrets, portée

Portées minimales : read-only access to Prometheus API

Stockage des identifiants : Bearer token or basic auth in env; mTLS cert paths if used

Sortie de données : Your Prometheus URL only

Dépannage

Erreurs courantes et correctifs

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

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

Alternatives

prometheus-mcp-server vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills