BloodHound-MCP-AI
Analyze BloodHound Active Directory attack paths with natural language via 75+ Cypher-backed MCP tools.
Add to your client
Copy the config for your MCP client and paste it into its config file.
git clone https://github.com/MorDavid/BloodHound-MCP-AI.git && pip install -r requirements.txtPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"bloodhound-mcp-ai": {
"command": "python",
"args": [
"<Your_Path>\\BloodHound-MCP.py"
],
"env": {
"BLOODHOUND_URI": "bolt://localhost:7687",
"BLOODHOUND_USERNAME": "neo4j",
"BLOODHOUND_PASSWORD": "bloodhoundcommunityedition"
}
}
}
}Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- BloodHound 4.x+ with data collected from an Active Directory environment
- Neo4j database with BloodHound data loaded
- Python 3.8 or higher
- An MCP client (e.g. Claude Desktop, Cursor)
About BloodHound-MCP-AI
BloodHound-MCP-AI is a Python MCP server that wraps BloodHound's Neo4j graph database with 75+ tools based on BloodHound CE Cypher queries, letting AI assistants answer Active Directory attack-path and security-posture questions in natural language over a stdio transport.
Tools & capabilities (8)
Domain structure mappingQuery and map the structure of Active Directory domains, users, groups, computers, and their relationships.
Privilege escalation pathsDiscover attack paths to high-value targets such as Domain Admins, including where Domain Users have local admin rights.
Kerberos security analysisIdentify Kerberos issues including Kerberoastable users and AS-REP Roasting candidates and their paths to privileged accounts.
Certificate services (ADCS) analysisMap Active Directory Certificate Services vulnerabilities and abuse opportunities.
Active Directory hygiene assessmentAssess AD hygiene, e.g. finding inactive privileged accounts and other posture weaknesses.
NTLM relay attack analysisIdentify domain controllers and other targets vulnerable to NTLM relay attacks.
Delegation abuse analysisDiscover delegation abuse opportunities (e.g. unconstrained/constrained/resource-based delegation).
Security report generationGenerate comprehensive natural-language security reports about a domain for stakeholders.
When to use it
- Run Active Directory attack-path analysis in plain English without writing Cypher queries
- Find paths from kerberoastable users to Domain Admins
- Identify computers where Domain Users have local admin rights
- Detect domain controllers vulnerable to NTLM relay attacks
- Map ADCS certificate-services vulnerabilities
- Generate domain security reports and surface inactive privileged accounts
Security notes
Connects to a Neo4j database holding BloodHound Active Directory data; configured with Neo4j credentials passed via env (BLOODHOUND_URI, BLOODHOUND_USERNAME, BLOODHOUND_PASSWORD). This is an offensive-security analysis tool: only run it against environments you are explicitly authorized to assess, treat BloodHound data as sensitive, and follow responsible-disclosure practices for any vulnerabilities found.
BloodHound-MCP-AI FAQ
What does this server connect to?
It connects to the Neo4j graph database that BloodHound uses to store Active Directory relationship data, over the Bolt protocol. You provide the URI, username, and password via environment variables.
Does it need an API key?
No. Authentication is to your local Neo4j/BloodHound database via Neo4j credentials (env vars), not an external API key.
How many tools does it provide?
Over 75 specialized tools based on the original BloodHound CE Cypher queries, spanning domain mapping, privilege escalation, Kerberos, certificate services, AD hygiene, NTLM relay, and delegation abuse.
Is this an official BloodHound or Anthropic product?
No. It is a community-driven integration and is not an official Anthropic or BloodHound vendor product.
Alternatives to BloodHound-MCP-AI
Compare all alternatives →
Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).
Up-to-date, version-specific library documentation injected into your coding agent.
Code intelligence engine that indexes repos into a persistent knowledge graph for AI coding agents.
Compare BloodHound-MCP-AI with: