Wazuh Autopilot

gensecaihq60stars

1# Wazuh Autopilot

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-27

Stars: 60
Tools: —
Uptime: —

Overview

About Wazuh Autopilot

Agentic SOC for Wazuh built on Strands Agents: a 13-agent swarm with 37 Wazuh-verified skills triages, investigates and plans response through the Wazuh MCP Server. Policy-gated autonomy, approvals, RBAC, audit, tracing and evals in one Docker stack. Bedrock, Anthropic, NVIDIA NIM, vLLM, LiteLLM or air-gapped Ollama.

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Wazuh Autopilot?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Wazuh Autopilot need an API key?

No required environment variable is listed on this record.

What transport does Wazuh Autopilot use?

Wazuh Autopilot runs locally over stdio.

When was Wazuh Autopilot last checked?

Last checked 2026-10-27. Agentic SOC for Wazuh built on Strands Agents: a 13-agent swarm with 37 Wazuh-verified skills triages, investigates and plans response through the Wazuh MCP Server. Policy-gated autonomy, approvals, RBAC, audit, tracing and evals in one Docker stack. Bedrock, Anthropic, NVIDIA NIM, vLLM, LiteLLM or air-gapped Ollama.

From the publisher

Documentation

Wazuh Autopilot is a self-hosted platform that works your Wazuh alerts with a swarm of Strands agents. They reach Wazuh only through the Wazuh MCP Server (v4.3.0, 55 tools). Alerts become incidents. Agents triage, correlate, investigate, enrich and plan the response, and every containment step goes through an autonomy policy you control, from "observe only" to "fully autonomous for low-risk actions". Everything runs in one container plus Postgres and ships with a web console.

⚡ Minutes, not hours · 🤖 13 agents / 37 skills · 🧭 NIST · MITRE · CIS · ISO · PCI · ✅ Policy-gated response · 🔭 Full tracing · 🔒 Air-gap ready

Quick start

git clone https://github.com/gensecaihq/Wazuh-Autopilot.git && cd Wazuh-Autopilot
docker compose -f docker-compose.yml -f docker-compose.demo.yml up -d --build
open http://localhost:8480     # [email protected] / Autopilot!2026

The demo runs against a simulated Wazuh fleet (mock-wazuh/: same tools and schemas as the real MCP server, live alerts, two planted compromises) and a scripted demo model, so it needs neither Wazuh nor an LLM key. Tool calls, policy decisions, approvals, execution and verification are all real. To see real reasoning, pick a model in Settings → Models.

For production, cp .env.example .env, point it at your Wazuh MCP Server and model provider, and run docker compose up -d. The first visit opens the setup wizard. See docs/QUICKSTART.md and docs/DEPLOYMENT.md.

Before enabling active response: the MCP key needs wazuh:write scope, and isolate_host, kill_process and quarantine_file rely on active-response scripts that don't ship with Wazuh, so deploy them on your agents first (details).

Upgrading from 1.x: 3.0 replaces the Node Runtime Service and the OpenClaw, Hermes and NemoClaw profiles with the Strands platform, and there's no in-place migration. Deploy 3.0 next to your existing install, point it at the same Wazuh MCP Server, and retire the old one once you're happy. Details in the changelog.

What you get


Agent swarm	SOC Commander, Tier 1–3 analysts, CTI analyst, threat hunter, vulnerability manager, IR lead, SecOps engineer, detection engineer, GRC analyst, Wazuh platform engineer and SOC manager. Workflows run as a Strands `Swarm` (agents hand off to each other) or a `Graph` (fixed pipeline).
Skills	37 Agent Skills (`SKILL.md`): 9 Wazuh-specific skills (MCP querying, rules and decoders, FIM, SCA, malware, Windows/Sysmon, cloud and containers, active response, platform health), 7 incident-response playbooks (brute force, lateral movement, privilege escalation, ransomware, suspicious PowerShell, data exfiltration, vulnerability spike). Agents load them on demand. Every Wazuh rule ID the skills cite is checked against the official Wazuh 4.14 ruleset in CI.
Standards	NIST CSF 2.0, SP 800-61r3, SP 800-53r5, MITRE ATT&CK and D3FEND, CIS v8.1, ISO/IEC 27001:2022, PCI DSS v4.0.1, SANS PICERL, CISA KEV / FIRST EPSS / SSVC, Sigma, OWASP LLM Top 10.
Autonomy policy	Four levels: observe, recommend, supervised, autonomous. Plus per-action rules (confidence floor, hourly budget), per-agent caps, protected targets, a two-person rule and a business-hours limit. Critical actions always need a human.
Safe by construction	Agents never receive state-changing Wazuh tools: the MCP tool filter and a pre-tool hook both block them. The platform runs approved actions, verifies them with `wazuh_check_*`, and can roll them back.
Console	Command center, alerts, incidents, approvals, agent roster, swarm topology, skills, workflows, agent playground/debugger, evals, run traces, metrics, agent health, policy, standards coverage, audit log, settings, users/roles/API tokens, setup wizard.
Models	Amazon Bedrock (with Guardrails), Anthropic, OpenAI-compatible, NVIDIA NIM (Nemotron), vLLM, LiteLLM, Ollama. Swarm-wide default with per-agent overrides.
Operations	RBAC (5 roles), audit log, Postgres, OpenTelemetry export, Prometheus `/metrics`, `strands-agents-evals` suites, restart recovery, trace retention.

How it works

Wazuh ──► Wazuh MCP Server ◄──────────────── agents (read + verify tools only)
              ▲      │ alerts (poll or webhook)
              │      ▼
              │   Autopilot ── incidents ──► Strands swarm: triage → correlation → investigation → CTI → IR lead
              │      │                                                   │ propose_action
              │      ▼                                                   ▼
              └── executor ◄── approved ◄── autonomy policy ── approvals queue (humans)
                     └── verify (wazuh_check_*) · audit · rollback

Details in docs/ARCHITECTURE.md.

Repository layout

backend/        FastAPI + Strands swarm, policy engine, executor (Python 3.12)
  app/skills/   37 SKILL.md skills
  tests/        pytest suite
ui/             React + TypeScript console
mock-wazuh/     simulated Wazuh MCP server for demos and tests
litellm/        LiteLLM proxy config (compose profile)
docs/           documentation

Documentation


QUICKSTART.md	Demo and first production install
DEPLOYMENT.md	Production deployment, ingestion, operations
ARCHITECTURE.md	Components, data flow, security boundaries
AGENTS_AND_SKILLS.md	Roster, skills, workflows, standards
AUTONOMY_AND_APPROVALS.md	Autonomy levels, action rules, approvals, execution and verification
MODEL_PROVIDERS.md	Bedrock, Anthropic, OpenAI-compatible, NVIDIA NIM, vLLM, LiteLLM, Ollama, air-gapped
MCP_INTEGRATION.md	Connecting the Wazuh MCP Server
TAILSCALE_MANDATORY.md	Network isolation
API.md	REST API (OpenAPI at `/api/docs`)
TROUBLESHOOTING.md	Common problems

Development

cd backend && python3.12 -m venv .venv && . .venv/bin/activate
pip install -r requirements-dev.txt && pytest -q
cd ../ui && npm ci && npm run build

See CONTRIBUTING.md. The PyPI package is strands-agents: pip install strands installs an unrelated library, and strands-evals isn't the official evals package (strands-agents-evals is).

Acknowledgments

Thanks to @idrone3d for thorough field testing on self-hosted hardware and the findings in issue #33: idle inference cost from timer-driven agents, new alerts being grouped into closed cases, and proposals surviving expiry across restarts. The platform has no heartbeat polling: agents run on incidents, and the scheduled workflows (hunts, sweeps, briefings, platform-health checks; about a dozen runs a day by default) can be disabled or rescheduled in Workflows. It groups alerts only into open incidents and stores proposal expiry in the database.

Related projects

Project	Description
Wazuh MCP Server	MCP bridge for the Wazuh API (55 tools, RBAC, audit logging)
Strands Agents	Open-source agent SDK the swarm is built on

License

MIT, see LICENSE.

Wazuh Autopilot

gensecaihq60stars

Devops Autonomous Agents

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# Wazuh Autopilot

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-27

Stars: 60
Tools: —
Uptime: —

Overview

About Wazuh Autopilot

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Wazuh Autopilot?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Wazuh Autopilot need an API key?

No required environment variable is listed on this record.

What transport does Wazuh Autopilot use?

Wazuh Autopilot runs locally over stdio.

When was Wazuh Autopilot last checked?

From the publisher

Documentation

⚡ Minutes, not hours · 🤖 13 agents / 37 skills · 🧭 NIST · MITRE · CIS · ISO · PCI · ✅ Policy-gated response · 🔭 Full tracing · 🔒 Air-gap ready

Quick start

git clone https://github.com/gensecaihq/Wazuh-Autopilot.git && cd Wazuh-Autopilot
docker compose -f docker-compose.yml -f docker-compose.demo.yml up -d --build
open http://localhost:8480     # [email protected] / Autopilot!2026

What you get


Agent swarm	SOC Commander, Tier 1–3 analysts, CTI analyst, threat hunter, vulnerability manager, IR lead, SecOps engineer, detection engineer, GRC analyst, Wazuh platform engineer and SOC manager. Workflows run as a Strands `Swarm` (agents hand off to each other) or a `Graph` (fixed pipeline).
Skills	37 Agent Skills (`SKILL.md`): 9 Wazuh-specific skills (MCP querying, rules and decoders, FIM, SCA, malware, Windows/Sysmon, cloud and containers, active response, platform health), 7 incident-response playbooks (brute force, lateral movement, privilege escalation, ransomware, suspicious PowerShell, data exfiltration, vulnerability spike). Agents load them on demand. Every Wazuh rule ID the skills cite is checked against the official Wazuh 4.14 ruleset in CI.
Standards	NIST CSF 2.0, SP 800-61r3, SP 800-53r5, MITRE ATT&CK and D3FEND, CIS v8.1, ISO/IEC 27001:2022, PCI DSS v4.0.1, SANS PICERL, CISA KEV / FIRST EPSS / SSVC, Sigma, OWASP LLM Top 10.
Autonomy policy	Four levels: observe, recommend, supervised, autonomous. Plus per-action rules (confidence floor, hourly budget), per-agent caps, protected targets, a two-person rule and a business-hours limit. Critical actions always need a human.
Safe by construction	Agents never receive state-changing Wazuh tools: the MCP tool filter and a pre-tool hook both block them. The platform runs approved actions, verifies them with `wazuh_check_*`, and can roll them back.
Console	Command center, alerts, incidents, approvals, agent roster, swarm topology, skills, workflows, agent playground/debugger, evals, run traces, metrics, agent health, policy, standards coverage, audit log, settings, users/roles/API tokens, setup wizard.
Models	Amazon Bedrock (with Guardrails), Anthropic, OpenAI-compatible, NVIDIA NIM (Nemotron), vLLM, LiteLLM, Ollama. Swarm-wide default with per-agent overrides.
Operations	RBAC (5 roles), audit log, Postgres, OpenTelemetry export, Prometheus `/metrics`, `strands-agents-evals` suites, restart recovery, trace retention.

How it works

Wazuh ──► Wazuh MCP Server ◄──────────────── agents (read + verify tools only)
              ▲      │ alerts (poll or webhook)
              │      ▼
              │   Autopilot ── incidents ──► Strands swarm: triage → correlation → investigation → CTI → IR lead
              │      │                                                   │ propose_action
              │      ▼                                                   ▼
              └── executor ◄── approved ◄── autonomy policy ── approvals queue (humans)
                     └── verify (wazuh_check_*) · audit · rollback

Details in docs/ARCHITECTURE.md.

Repository layout

backend/        FastAPI + Strands swarm, policy engine, executor (Python 3.12)
  app/skills/   37 SKILL.md skills
  tests/        pytest suite
ui/             React + TypeScript console
mock-wazuh/     simulated Wazuh MCP server for demos and tests
litellm/        LiteLLM proxy config (compose profile)
docs/           documentation

Documentation


QUICKSTART.md	Demo and first production install
DEPLOYMENT.md	Production deployment, ingestion, operations
ARCHITECTURE.md	Components, data flow, security boundaries
AGENTS_AND_SKILLS.md	Roster, skills, workflows, standards
AUTONOMY_AND_APPROVALS.md	Autonomy levels, action rules, approvals, execution and verification
MODEL_PROVIDERS.md	Bedrock, Anthropic, OpenAI-compatible, NVIDIA NIM, vLLM, LiteLLM, Ollama, air-gapped
MCP_INTEGRATION.md	Connecting the Wazuh MCP Server
TAILSCALE_MANDATORY.md	Network isolation
API.md	REST API (OpenAPI at `/api/docs`)
TROUBLESHOOTING.md	Common problems

Development

cd backend && python3.12 -m venv .venv && . .venv/bin/activate
pip install -r requirements-dev.txt && pytest -q
cd ../ui && npm ci && npm run build

See CONTRIBUTING.md. The PyPI package is strands-agents: pip install strands installs an unrelated library, and strands-evals isn't the official evals package (strands-agents-evals is).

Acknowledgments

Related projects

Project	Description
Wazuh MCP Server	MCP bridge for the Wazuh API (55 tools, RBAC, audit logging)
Strands Agents	Open-source agent SDK the swarm is built on

License

MIT, see LICENSE.