{"id":"mwnickerson-bloodhound-mcp","name":"bloodhound_mcp","af_score":60.5,"security_score":58.2,"reliability_score":25.0,"what_it_does":"Provides an MCP server that lets an AI assistant query BloodHound Community Edition data (via BloodHound CE REST API and Neo4j graph) through a set of composite MCP tools (e.g., domain/user/group/computer info, graph analysis, ADCS info, and Cypher execution) and reference resources for Cypher and AD/ADCS/Azure methodology.","best_when":"Used in lab/non-production environments with appropriate API-token scoping and when an operator understands the security implications of sending BloodHound-derived data to an LLM.","avoid_when":"Avoid when BloodHound datasets include sensitive production identities/relationships and you have not assessed exposure to your LLM provider; also avoid when robust guardrails for Cypher execution are not in place.","last_evaluated":"2026-03-30T13:51:57.130420+00:00","has_mcp":true,"has_api":true,"auth_methods":["BloodHound API token (Token ID + Token Key) via .env"],"has_free_tier":false,"known_gotchas":["The tool surface includes `cypher_query` and `custom_nodes` which can increase risk if used without guardrails","The README references a 'system prompt' tuned for offensive security analysis; agents may follow methodology rules that are not appropriate for all environments"],"error_quality":0.0}