wazuh-mcp-server

Provides a Model Context Protocol (MCP) server that exposes Wazuh Manager and syscollector data (agents, ports, packages, processes, rules, rule files, and SCA results) as MCP tools, including an authentication tool to refresh JWT tokens used to call the Wazuh Manager API.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ Security mcp wazuh siem llm-integration security-analytics python syscollector jwt
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
56
/ 100
Is it safe for agents?
⚡ Reliability
35
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
65
Rate Limits
5

🔒 Security

TLS Enforcement
80
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
60
Secret Handling
55

Claims 'Secure: JWT token management with automatic refresh' and provides WAZUH_* credentials via env vars, but does not document MCP-side access control, authorization scopes per tool, or logging/redaction behavior. WAZUH_PROD_SSL_VERIFY defaults to true but can be disabled; that increases risk if misconfigured. Rate limiting and protection against abusive queries are not described.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
45
Error Recovery
50
AF Security Reliability

Best When

You control the runtime environment (network access, secrets, and Wazuh credentials) and want an MCP tool interface for an LLM to reason over Wazuh data.

Avoid When

You cannot restrict access to the MCP server and Wazuh credentials, or you need strict guarantees around error codes, retry semantics, and pagination behavior beyond the stated defaults.

Use Cases

  • Ask an LLM questions about Wazuh-monitored infrastructure (agents status, listening ports, running processes)
  • Generate and validate incident context by pulling Wazuh rules and rule file content
  • Query syscollector data for forensic triage (packages/processes/ports per agent)
  • Automate security configuration assessment (SCA) lookups via natural language

Not For

  • Public internet deployment without network controls (it binds to a host/port and relies on operational security)
  • Use as a general-purpose Wazuh API client without understanding Wazuh permissions and data exposure
  • Use where you require documented rate-limit behavior, idempotency guarantees, or strong operational SLAs from the MCP layer

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Wazuh username/password to obtain/refresh JWT for Wazuh Manager API
OAuth: No Scopes: No

README states JWT token management with automatic refresh and includes an AuthenticateTool to force JWT refresh. No user-facing MCP auth mechanism is described (i.e., who can call the MCP server).

Pricing

Free tier: No
Requires CC: No

Self-hosted open-source (license shown as AGPL-3.0 in repo metadata; manifest snippet shows MIT but that is untrusted data). Costs are mainly infrastructure and Wazuh operations; no external pricing described.

Agent Metadata

Pagination
offset/limit (offset and limit parameters across many tools; defaults stated as limit=500 offset=0)
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP auth layer is not described; ensure access to the MCP endpoint is restricted (network/firewall, bind address).
  • Some tools can trigger expensive Wazuh queries (rules listing, syscollector queries per agent); use limit/offset and filtering parameters carefully.
  • Token refresh is exposed via AuthenticateTool; agents may need to call it when encountering auth failures.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for wazuh-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6510
Packages Evaluated
19893
Need Evaluation
586
Need Re-evaluation
Community Powered