Query domain level data from BloodHound info_type options: list - list all domains (no domain_id needed) search - search objects by name/ID (needs query param, domain_id not needed) users - users in the domain groups - groups in the domain computers - computers in the domain controllers - securit...
AI agents call domain_info to retrieve information from BloodHound MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries Active Directory attack path data without modifying, deleting, or executing operations. While the data exposed (DCSync rights, admin relationships, security principals) is sensitive and could inform malicious actions, the tool itself only reads information.
From the tool's definition Tool performs queries on BloodHound data with info_type options including 'list', 'search', 'users', 'groups', 'computers', 'controllers', 'gpos', 'ous', 'dc_syncers', 'foreign_admins', 'foreign_gpo_controllers' — all retrieval operations.
Documented attack patterns abuse exactly the kind of access domain_info 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 domain_info:
{
"version": "1",
"default": "deny",
"tools": {
"domain_info": {}
}
}domain_info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Query domain level data from BloodHound info_type options: list - list all domains (no domain_id needed) search - search objects by name/ID (needs query param, domain_id not needed) users - users in the domain groups - groups in the domain computers - computers in the domain controllers - security prinicpals with control relationships gpos - Group Policy Objects ous - Organizational unites dc_syncers - Principals with DCSync rights foreign_admins - admins from other domains foreign_gpo_controllers - GPO controllers from other domains foreign_groups - groups with cross domain members foreign_users - users referenced across domains inbound_trusts - domains that trust this domain outbound_trusts - domains this domain trusts Args: info_type: what to retrieve (default: list) domain_id: Domain object ID (required for most info_types) query: Search text (for info_type=search only) object_type: Filter by type - User, computer, Group, GPO, OU, Domain, AZUer, etc. (search only) limit: Max Results (default 100, useful in large environments) skip: Pagination offset (default 0). It is categorised as a Read tool in the BloodHound MCP Server MCP Server, which means it retrieves data without modifying state.
Register the BloodHound MCP Server MCP server in PolicyLayer and add a rule for domain_info: 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.
domain_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the domain_info 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 domain_info. 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.
domain_info 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.