prometheus-mcp-server MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

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

Demo ao vivo

Como fica na prática

prometheus.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: prometheus-mcp-server

How to diagnose a latency spike with Prometheus + Claude

👤 On-call SREs ⏱ ~10 min intermediate

Quando usar: A service p99 alert fires — you need context without memorizing PromQL.

Pré-requisitos

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

Fluxo

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.✓ Copiado

→ 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?✓ Copiado

→ Candidate culprit metrics
Narrow by label

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

→ Per-label decomposition

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

Armadilhas

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

Combine com: kubectl

Generate a weekly SLO compliance report from Prometheus

👤 SRE leads ⏱ ~25 min intermediate

Quando usar: Friday SLO review — you want numbers not vibes.

Fluxo

Define the SLIs

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

→ Two ratios with burn rate
Compare to SLO

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

→ Verdict + days of budget remaining

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

Combine com: google-sheets

Audit Prometheus scrape target health with Claude

👤 Platform engineers ⏱ ~15 min intermediate

Quando usar: You suspect half your targets are down but haven't checked.

Fluxo

Get targets

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

→ Table of job → up/down counts
Investigate

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

→ Actionable cause per target

Resultado: Rescued scrapes in minutes.

Combinações

Combine com outros MCPs para 10× de alavancagem

prometheus + kubectl

Pair metric anomalies with pod state

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

prometheus + sentry

Metric spike + error spike correlation

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

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

Cota de API: Prometheus scales with your server; expensive queries can stress it
Tokens por chamada: Range queries with many series can hit 10k+ tokens
Monetário: Free
Dica: Use step wisely on range queries; 10s resolution over 24h is 8640 samples per series

Segurança

Permissões, segredos, alcance

Escopos mínimos: read-only access to Prometheus API

Armazenamento de credenciais: Bearer token or basic auth in env; mTLS cert paths if used

Saída de dados: Your Prometheus URL only

Solução de problemas

Erros comuns e correções

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

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

Alternativas

prometheus-mcp-server vs. outros

Alternativa	Quando usar	Troca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills