Query group data from BloodHound. info_type options: info - general group properties and attributes admin_rights - machine/objects this group has admin rights on controllables - objects this group can control controllers - principals that have control over this group dcom_rights - machines this g...
AI agents call group_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 group data from BloodHound, including membership, rights, and relationships. It performs read-only operations with no side effects. However, it has medium severity because the data exposed (admin rights, controllables, DCOM/PSRemote/RDP rights) is highly sensitive security intelligence that could be used to map attack paths in Active Directory environments.
From the tool's definition Query group data from BloodHound... info - general group properties and attributes, members - users and groups that are members of this group, memberships - groups this group belongs to
Risk signalsAdmin/system-level operation
Documented attack patterns abuse exactly the kind of access group_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 group_info:
{
"version": "1",
"default": "deny",
"tools": {
"group_info": {}
}
}group_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 group data from BloodHound. info_type options: info - general group properties and attributes admin_rights - machine/objects this group has admin rights on controllables - objects this group can control controllers - principals that have control over this group dcom_rights - machines this group can execute DCOM on members - users and groups that are members of this group memberships - groups this group belongs to (nested membership) ps_remote_rights - machines this group can PSRemote to rdp_rights - machines this group can RDP to sessions - machines this group has active sessions on args: group_id: BloodHound object ID of the group (required) info_type: what to retrieve (default: info) 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 group_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.
group_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 group_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 group_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.
group_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.