BloodHound-MCP

To install BloodHound-MCP, clone the repository, navigate to the directory, and install the required Python dependencies using pip.

Prerequisites

• BloodHound 4.x+ with Active Directory data.
• A Neo4j database with BloodHound data loaded.
• Python 3.8 or higher.
• An MCP Client (e.g., Claude Desktop).

git clone https://github.com/your-username/MCP-BloodHound.git
cd MCP-BloodHound
pip install -r requirements.txt

To use BloodHound-MCP with an MCP client, add the server configuration to your client's configuration file. You must provide the absolute path to the BloodHound-MCP.py script and set the necessary environment variables to connect to your Neo4j database.

Environment Variables:

• BLOODHOUND_URI: The connection string for your Neo4j instance (e.g., bolt://localhost:7687).
• BLOODHOUND_USERNAME: The Neo4j username (default is often neo4j).
• BLOODHOUND_PASSWORD: The password for the Neo4j user.

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

Once configured, you can interact with BloodHound data using plain English through your MCP-compatible AI client. The server provides over 75 specialized tools based on BloodHound CE Cypher queries to perform various security analyses.

Example queries include:

• "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"