wazuh-mcp
An MCP server for the Wazuh SIEM/XDR platform that enables users to query agents, security alerts, detection rules, and decoders through Claude or other MCP clients. It provides specialized tools and prompts for investigating security alerts, performing agent health checks, and generating environmental security overviews.
README
wazuh-mcp
A Model Context Protocol (MCP) server for the Wazuh SIEM/XDR platform. Query agents, security alerts, detection rules, and decoders directly from Claude or any MCP-compatible client.
Features
- 11 MCP Tools - Agents, alerts, rules, decoders, and version info
- 3 MCP Resources - Pre-built views for agents, recent alerts, and rule summaries
- 3 MCP Prompts - Alert investigation, agent health checks, and security overviews
- JWT Authentication - Automatic token management with refresh on expiry
- Full Compliance Mapping - PCI-DSS, GDPR, HIPAA, NIST 800-53, MITRE ATT&CK
- Pagination - All list endpoints support limit/offset pagination
- Type-Safe - Full TypeScript with strict mode and Zod schema validation
Prerequisites
- Node.js 20+
- A running Wazuh manager with API access (default port 55000)
- Wazuh API credentials (username/password)
Installation
git clone https://github.com/solomonneas/wazuh-mcp.git
cd wazuh-mcp
npm install
npm run build
Configuration
Set the following environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
WAZUH_URL |
Yes | - | Wazuh API URL (e.g., https://10.0.0.2:55000) |
WAZUH_USERNAME |
Yes | - | API username |
WAZUH_PASSWORD |
Yes | - | API password |
WAZUH_VERIFY_SSL |
No | false |
Set to true to verify SSL certificates |
Alternative variable names WAZUH_BASE_URL and WAZUH_USER are also supported.
Usage
Claude Desktop
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"wazuh": {
"command": "node",
"args": ["/path/to/wazuh-mcp/dist/index.js"],
"env": {
"WAZUH_URL": "https://your-wazuh-manager:55000",
"WAZUH_USERNAME": "wazuh-wui",
"WAZUH_PASSWORD": "your-password"
}
}
}
}
Standalone
export WAZUH_URL=https://your-wazuh-manager:55000
export WAZUH_USERNAME=wazuh-wui
export WAZUH_PASSWORD=your-password
npm start
Development
npm run dev # Watch mode with tsx
npm run lint # Type checking
npm test # Run tests
MCP Tools
Agent Tools
| Tool | Description |
|---|---|
list_agents |
List all agents with optional status filtering (active, disconnected, never_connected, pending) |
get_agent |
Get detailed info for a specific agent by ID |
get_agent_stats |
Get CPU, memory, and disk statistics for an agent |
Alert Tools
| Tool | Description |
|---|---|
get_alerts |
Retrieve recent alerts with filtering by level, agent, rule, and text search |
get_alert |
Retrieve a single alert by ID |
search_alerts |
Full-text search across all alerts |
Rule Tools
| Tool | Description |
|---|---|
list_rules |
List detection rules with level and group filtering |
get_rule |
Get full rule details including compliance mappings |
search_rules |
Search rules by description text |
Other Tools
| Tool | Description |
|---|---|
list_decoders |
List log decoders with optional name filtering |
get_wazuh_version |
Get Wazuh manager version and API info |
MCP Resources
| Resource URI | Description |
|---|---|
wazuh://agents |
All registered agents and their status |
wazuh://alerts/recent |
25 most recent security alerts |
wazuh://rules/summary |
Detection rules sorted by severity |
MCP Prompts
| Prompt | Description |
|---|---|
investigate-alert |
Step-by-step alert investigation with MITRE mapping and remediation |
agent-health-check |
Comprehensive agent health assessment (status, resources, alerts) |
security-overview |
Full environment security summary with compliance coverage |
Examples
List active agents
Use list_agents with status "active" to see all connected agents.
Investigate a brute force attempt
Search alerts for "brute force" and investigate the top result,
including the MITRE ATT&CK technique and remediation steps.
Check agent health
Run an agent health check on agent 001 - check its connection status,
resource usage, and any recent critical alerts.
Find high-severity rules
List all rules with level 12 or higher to see critical detection rules
and their compliance framework mappings.
Testing
npm test # Run all tests
npm run test:watch # Watch mode
Tests use mocked Wazuh API responses - no live Wazuh instance needed.
Project Structure
wazuh-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── config.ts # Environment configuration
│ ├── client.ts # Wazuh REST API client (JWT auth)
│ ├── types.ts # TypeScript type definitions
│ ├── resources.ts # MCP resource handlers
│ ├── prompts.ts # MCP prompt templates
│ └── tools/
│ ├── agents.ts # Agent management tools
│ ├── alerts.ts # Alert query tools
│ ├── rules.ts # Rule query tools
│ ├── decoders.ts # Decoder listing tool
│ └── version.ts # Version info tool
├── tests/
│ ├── client.test.ts # API client unit tests
│ └── tools.test.ts # Tool handler unit tests
├── package.json
├── tsconfig.json
├── tsup.config.ts
└── vitest.config.ts
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.