MCP Server is a backend service that powers the Model Context Protocol, allowing Claude AI to securely access data, call tools, and execute tasks. It enables AI models to interact with external services like monitoring tools, databases, and analysis engines while maintaining controlled access to system resources.
To get started with MCP, install the Python SDK using pip:
pip install modelcontextprotocol
First, download and install Claude Desktop from the official website: https://www.anthropic.com/index/claude-desktop
After installation, you'll need to configure Claude to connect with your MCP server:
For macOS/Linux:
nano ~/Library/Application\ Support/Claude/claude_desktop_config.json
For Windows:
notepad %AppData%\Claude\claude_desktop_config.json
Add your MCP server configuration to the JSON file:
{
"mcpServers": {
"my-wazuh-agent": {
"command": "/full/path/to/python",
"args": [
"mcp_wazuh_server.py"
]
}
}
}
Save the file and restart Claude Desktop. When configured correctly, you'll see the connector icon (⚡) for prompts and the tools icon (🛠) for tool invocation in the Claude interface.
Before connecting your MCP server to Claude, you can test it locally using the MCP Inspector:
npx @modelcontextprotocol/inspector python mcp_wazuh_server.py
This command launches a local web interface that allows you to test @mcp.tool()
and @mcp.prompt()
functionality before integrating with Claude.
Once your server is properly configured and connected to Claude Desktop, you can:
The MCP server can be configured to support various cybersecurity workflows:
Each use case requires specific configuration of your MCP server to expose the relevant tools and resources to Claude.
For more detailed documentation on setting up and using MCP servers, visit: https://modelcontextprotocol.io/quickstart/server
The FastMCP library provides additional functionality for creating MCP servers: https://github.com/jlowin/fastmcp
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "offensive-mcp-ai" '{"command":"python","args":["mcp_wazuh_server.py"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"offensive-mcp-ai": {
"command": "python",
"args": [
"mcp_wazuh_server.py"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"offensive-mcp-ai": {
"command": "python",
"args": [
"mcp_wazuh_server.py"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect