Happy slice of mcp pizzaMCP.pizza

BloodHound-MCP-AI

MCP.Pizza Chef: MorDavid

BloodHound is the tool security teams use to map who can reach what inside a company's Windows network. This add-on hands that map to your assistant, so instead of writing database queries you can ask which accounts could reach a domain administrator, which machines ordinary staff can log into, or which forgotten privileged accounts nobody has closed. It reads a BloodHound database already running on your own machine. Note that the project has had no code changes since June 2025.

Unmaintained · no commits since June 2025; no replacement named
Data
Other

Use This MCP server To

Find every path that leads from a normal account to admin Spot privileged accounts nobody has signed into for months Check which computers ordinary staff can log into as administrator Ask which domain controllers are exposed to relay attacks Write up a plain-English security report for my manager

README

BloodHound-MCP

BloodHound-MCP

Model Context Protocol (MCP) Server for BloodHound

BloodHound-MCP is a powerful integration that brings the capabilities of Model Context Procotol (MCP) Server to BloodHound, the industry-standard tool for Active Directory security analysis. This integration allows you to analyze BloodHound data using natural language, making complex Active Directory attack path analysis accessible to everyone.

🥇 First-Ever BloodHound AI Integration!
This is the first integration that connects BloodHound with AI through MCP, originally announced here.

🔍 What is BloodHound-MCP?

BloodHound-MCP combines the power of:

  • BloodHound: Industry-standard tool for visualizing and analyzing Active Directory attack paths
  • Model Context Protocol (MCP): An open protocol for creating custom AI tools, compatible with various AI models
  • Neo4j: Graph database used by BloodHound to store AD relationship data

With over 75 specialized tools based on the original BloodHound CE Cypher queries, BloodHound-MCP allows security professionals 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

📱 Community

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

🌟 Star History

Star History Chart

BloodHound-MCP-AI FAQ

Is this still maintained?
No new commits have landed since June 2025, so treat it as unmaintained. It still runs against a BloodHound Community Edition database, but nobody is shipping fixes, and the project does not name a replacement.
Can I use this to find attack paths without learning query languages?
Yes — that is the whole point. You ask in ordinary English and it runs the matching BloodHound query for you, drawing on roughly seventy-five built-in ones.
Which apps does it work in?
Any assistant that can run a local MCP server. The setup notes show the standard config block used by Claude Desktop and similar tools.
Do I need to sign up or pay for anything?
No account is needed. You do need your own BloodHound install with its Neo4j database running locally, plus that database's username and password.
How hard is setup?
This one is for technical users: you clone the repository, install Python packages, and point your assistant's config file at the script.
Do I need my own data first?
Yes — you must have already collected data from an Active Directory environment and loaded it into BloodHound. The tool reads that data, it does not gather it.