Wazuh-MCP-Server MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

48 tools across alerts, agents, vulnerabilities, active response, compliance
Output sanitization — redacts credentials before they reach the LLM
Rate limiting + circuit breakers to protect Wazuh Manager
RBAC per tool; audit logs for destructive actions
Deploys via Docker Compose; supports Wazuh 4.8–4.14

Demo en vivo

Cómo se ve en la práctica

wazuh.replay ▶ listo

0/0

Instalar

Elige tu cliente

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

{
  "mcpServers": {
    "wazuh": {
      "command": "uvx",
      "args": [
        "Wazuh-MCP-Server"
      ],
      "_inferred": true
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "wazuh": {
      "command": "uvx",
      "args": [
        "Wazuh-MCP-Server"
      ],
      "_inferred": true
    }
  }
}

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "wazuh": {
      "command": "uvx",
      "args": [
        "Wazuh-MCP-Server"
      ],
      "_inferred": true
    }
  }
}

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "wazuh": {
      "command": "uvx",
      "args": [
        "Wazuh-MCP-Server"
      ],
      "_inferred": true
    }
  }
}

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "wazuh",
      "command": "uvx",
      "args": [
        "Wazuh-MCP-Server"
      ]
    }
  ]
}

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

{
  "context_servers": {
    "wazuh": {
      "command": {
        "path": "uvx",
        "args": [
          "Wazuh-MCP-Server"
        ]
      }
    }
  }
}

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add wazuh -- uvx Wazuh-MCP-Server

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: Wazuh-MCP-Server

Triage overnight alerts in 10 minutes instead of 2 hours

👤 SOC analysts ⏱ ~20 min advanced

Cuándo usarlo: Shift start. Hundreds of alerts overnight. You need to find the real ones without reading every row.

Requisitos previos

Wazuh Manager API creds — Wazuh UI > API credentials

Flujo

Summarize

For last 12 hours: group alerts by rule group, count severity 10+ per group, top 5 agents with most high-sev alerts.✓ Copiado

→ Ranked summary
Investigate

For top agent, pull the 10 most recent high-sev alerts with full details.✓ Copiado

→ Detailed events
Determine action

Based on these events, is this a true positive? If yes, propose response: isolate agent / disable account / create ticket.✓ Copiado

→ Verdict + action plan

Resultado: Faster MTTD/MTTR without more eyeballs.

Errores comunes

Auto-triggering active response before confirming — Keep active response tools behind a confirmation gate

Weekly vulnerability posture report

👤 Security managers ⏱ ~30 min intermediate

Cuándo usarlo: Friday report for leadership. How many CVEs open? Where? Trend vs last week?

Flujo

Pull vulnerabilities

From Wazuh vulnerability module: total open CVEs by severity, top 10 agents by critical CVE count.✓ Copiado

→ Numbers + top agents
Compare to last week

Compare counts to last Friday's report [paste]. What improved, what regressed?✓ Copiado

→ Delta analysis
Prioritize

List the 5 critical CVEs affecting most hosts that should be patched this weekend.✓ Copiado

→ Actionable patch list

Resultado: Board-ready security posture summary.

Errores comunes

Vuln data only as fresh as last scan — Check scan timestamps before drawing conclusions

Combinar con: notion

Isolate a compromised host on confirmation

👤 SOC on-call ⏱ ~10 min advanced

Cuándo usarlo: Alert fires: unambiguous malware on endpoint. You need to isolate fast.

Flujo

Confirm scope

For agent 'ws-4412': show active processes with parent PID, recent listening ports, and last 20 alerts. Is this clearly compromised?✓ Copiado

→ Risk assessment
Isolate

Isolate agent ws-4412 via active response. Require my explicit confirm first.✓ Copiado

→ Confirmation prompt, then isolation + audit log entry

Resultado: Compromised host isolated within minutes.

Errores comunes

False-positive isolation of prod server — Double-check agent ID and classification before confirming; keep an out-of-band way to re-enable

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

wazuh + notion

Weekly security digest to exec

Compose a weekly Wazuh summary and create a Notion page in 'Security Weekly'.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
list_alerts	filter: obj, from, to, limit	Investigate by time/severity/rule	1 API call
get_agent	agent_id	Profile a specific endpoint	1 API call
list_vulnerabilities	agent_id?, severity?	Vuln posture checks	1 API call
trigger_active_response	agent_id, command, arguments?	Isolate / kill process / disable account — destructive; confirm	1 API call + physical effect
compliance_report	framework: 'pci'\|'hipaa'\|'nist', scope	Audit readiness	1 API call

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: Bounded by Wazuh Manager API limits
Tokens por llamada: Alert listings can be huge — always filter by time + severity
Monetario: Free. Wazuh itself is open-source.
Consejo: Use limit aggressively. Don't list a week's alerts without grouping.

Seguridad

Permisos, secretos, alcance

Ámbitos mínimos: Wazuh API user scoped read-only for inspection; elevate for active response

Almacenamiento de credenciales: Wazuh API creds in env or Docker secrets

Salida de datos: Alert/event data goes to your LLM provider

No conceder nunca: Active-response scope to a dev/eval instance

Active response tools cause real actions on endpoints. Gate behind human confirmation.
Alert payloads may contain sensitive info (filenames, users); consider Presidio-style redaction upstream.