Wazuh

Provides an MCP stdio server that wraps a local Wazuh agent script for prompt-driven control and testing.

python

19

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cybersecurityup-offensive-mcp-ai": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "python",
        "mcp_wazuh_server.py"
      ]
    }
  }
}

You can run this MCP server locally to connect your client workflows to a Wazuh-based agent, enabling automated tool orchestration and prompt-based interactions through the MCP framework. This server uses a stdio configuration to start a local process that the MCP client can drive from the inspector, making it convenient for testing and integration with Claude or other MCP-enabled clients.

How to use

To use this MCP server, run it through the MCP client so you can send prompts and tool invocations to the local Wazuh server process. The setup is designed for testing with the Inspector tool, which lets you interactively experiment with prompts and @mcp.tool() and @mcp.prompt() calls before connecting to a live Claude session.

How to install

Prerequisites: you need Python installed on your system and access to a Node.js-enabled environment for the MCP tooling. You will also use the MCP Inspector to test commands locally.

Install the MCP CLI and SDK using Python’s package manager.

{
  "mcpServers": {
    "wazuh_mcp": {
      "command": "npx",
      "args": ["@modelcontextprotocol/inspector", "python", "mcp_wazuh_server.py"]
    }
  }
}

Additional notes

The local test command to verify the setup is:

npx @modelcontextprotocol/inspector python mcp_wazuh_server.py


This opens a local UI where you can test `@mcp.tool()` and `@mcp.prompt()` before linking with Claude.

Security and troubleshooting

Ensure Python is installed and accessible in your PATH. - If the inspector UI cannot connect, verify that the mcp_wazuh_server.py script exists in your working directory and that Node.js/npm are installed for the MCP tooling. - For troubleshooting prompts and tool invocations, use the Inspector’s local UI to validate prompts before deploying to any remote MCP server.

Configuration reference

The following is the runtime configuration used to start the local Wazuh MCP server via the MCP Inspector. Use this exact structure in your configuration if you store MCP server settings in a JSON file.

Start command example

{
  "mcpServers": {
    "wazuh_mcp": {
      "command": "npx",
      "args": ["@modelcontextprotocol/inspector", "python", "mcp_wazuh_server.py"]
    }
  }
}