BloodHound MCP server

BloodHound-MCP is a powerful integration that connects BloodHound (the industry-standard tool for Active Directory security analysis) with AI capabilities through the Model Context Protocol (MCP). This integration allows you to analyze BloodHound data using natural language, making complex Active Directory attack path analysis more accessible and efficient.

What is BloodHound-MCP?

BloodHound-MCP combines BloodHound's visualization capabilities with MCP's natural language interface to provide security professionals with enhanced analysis tools. The integration leverages over 75 specialized tools based on BloodHound CE Cypher queries, enabling users to:

• Query BloodHound data using natural language
• Discover complex attack paths in Active Directory environments
• Assess Active Directory security posture more efficiently
• Generate detailed security reports for stakeholders

Prerequisites

Before installing BloodHound-MCP, ensure you have:

• BloodHound 4.x+ with data collected from an Active Directory environment
• Neo4j database with BloodHound data loaded
• Python 3.8 or higher
• MCP Client

Installation

Follow these steps to install BloodHound-MCP:

1. Clone the repository:

   git clone https://github.com/your-username/MCP-BloodHound.git
   cd MCP-BloodHound
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Configure the MCP Server by adding the following to your MCP configuration:

   "mcpServers": {
       "BloodHound-MCP": {
           "command": "python",
           "args": [
               "<Your_Path>\\BloodHound-MCP.py"
           ],
           "env": {
               "BLOODHOUND_URI": "bolt://localhost:7687",
               "BLOODHOUND_USERNAME": "neo4j",
               "BLOODHOUND_PASSWORD": "bloodhoundcommunityedition"
           }
       }
   }
   

Usage Examples

You can interact with BloodHound-MCP using natural language queries. Here are some example queries you can use:

• "Show me all paths from kerberoastable users to Domain Admins"
• "Find computers where Domain Users have local admin rights"
• "Identify Domain Controllers vulnerable to NTLM relay attacks"
• "Map all Active Directory certificate services vulnerabilities"
• "Generate a comprehensive security report for my domain"
• "Find inactive privileged accounts"
• "Show me attack paths to high-value targets"

Security Considerations

When using BloodHound-MCP, keep these security practices in mind:

• Always obtain proper authorization before analyzing any Active Directory environment
• Handle BloodHound data as sensitive information
• Follow responsible disclosure practices for any vulnerabilities discovered

Community

Join the Telegram channel for updates, tips, and discussion:

• Telegram: root_sec

How to add this MCP server to Cursor

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.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

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.

How to use the MCP server

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.