Execute and manage Cypher queries in BloodHound. info_type options: run - execute a cypher query (needs: query; optional: include_properties) interpret - interpret a natural language query into cypher (needs: query, result_json) list_saved - list saved queries (optional: name, skip, limit) create...
AI agents invoke cypher_query to trigger actions in BloodHound MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary Cypher queries against a BloodHound/Neo4j graph database containing sensitive Active Directory attack path data. The 'run' option executes raw queries with no described restrictions, meaning an AI agent could extract all AD credentials, attack paths, and privilege relationships, or potentially modify/delete graph data. It also includes destructive sub-operations ('delete_saved').
From the tool's definition 'run - execute a cypher query' and 'Execute and manage Cypher queries in BloodHound'
Documented attack patterns abuse exactly the kind of access cypher_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BloodHound MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cypher_query:
{
"version": "1",
"default": "deny",
"tools": {
"cypher_query": {
"limits": [
{
"counter": "cypher_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cypher_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute and manage Cypher queries in BloodHound. info_type options: run - execute a cypher query (needs: query; optional: include_properties) interpret - interpret a natural language query into cypher (needs: query, result_json) list_saved - list saved queries (optional: name, skip, limit) create_saved - save a new query (needs: name, query) get_saved - get details of a saved query (needs: query_id) update_saved - update an existing saved query (needs: query_id; optional: name, query, description) delete_saved - delete a saved query (needs: query_id) share_saved - share a saved query with other users (needs: query_id; optional: user_ids, public) validate - validate a cypher query for syntax and semantics (needs: query) args: info_type: Operation to perform query: Cypher query string (for run, create_saved, update_saved, validate) include_properties: Include node/edge properties in results (for run, default: True) name: Query name (for create_saved, update_saved, list_saved filter) query_id: Saved query ID (for get_saved, update_saved, delete_saved, share_saved) result_json: JSON result string from a previous run (for interpret) description: Query description (for update_saved) user_ids: Comma-separated user IDs to share with (for share_saved) public: Make query public (for share_saved, default: False) limit: Max results (default 100) skip: Pagination offset (default 0). It is categorised as a Execute tool in the BloodHound MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the BloodHound MCP Server MCP server in PolicyLayer and add a rule for cypher_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches BloodHound MCP Server. Nothing to install.
cypher_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cypher_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cypher_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cypher_query is provided by the BloodHound MCP Server MCP server (mwnickerson/bloodhound_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BloodHound MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 BloodHound MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.