Manage Asset isolation groups and tages in BloodHound info_type options: list - list all asset groups (optional filters: name, tag, sort_by, system_group) get - get a specific asset group (requires: asset_group_id) create - create a new asset group (requires: name, tag) update - update an existin...
AI agents call asset_groups to permanently remove resources in BloodHound MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool supports multiple operations including delete, which irreversibly removes asset groups. Following the most-severe-applicable rule, the presence of a delete operation classifies this as Destructive. In a BloodHound/Active Directory security context, deleting asset isolation groups could disrupt security monitoring and attack path analysis, with high blast radius if misused by an AI agent.
From the tool's definition delete - delete an asset group (requires: asset_group_id)
Documented attack patterns abuse exactly the kind of access asset_groups 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 asset_groups:
{
"version": "1",
"default": "deny",
"hide": [
"asset_groups"
]
}asset_groups disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Manage Asset isolation groups and tages in BloodHound info_type options: list - list all asset groups (optional filters: name, tag, sort_by, system_group) get - get a specific asset group (requires: asset_group_id) create - create a new asset group (requires: name, tag) update - update an existing asset group (requires: asset_group_id) delete - delete an asset group (requires: asset_group_id) collections - list historical membership snapshots (requires: asset_group_id) member_counts - get member counts by object type (requires: asset_group_id) update_selectors - set auto membership selectors (requires: asset_group_id, selectors_json) list_tags - list asset group tags (optional: name, tag, sort_by) create_tag - create a new asset group tag (requires: name, tag) tag_members - list members of a tag (requires: asset_group_tag_id) args: info_type: operation to perform (default: list) asset_group_id: Asset group ID (for get, update, delete, collections, member_counts, update_selectors) asset_group_tag_id: Tag ID (for tag_members) name: Group/tag name (for create, update, create_tag, or filters) tag: Tag value (for create, update, create_tag, or filters) sort_by: Sort field (for list, list tags) system_group: Filter by system group (for list) selectors_json: JSON array of selector specs (for update_selectors) skip: Pagination offset (default 0) limit: Max results (default 100). It is categorised as a Destructive tool in the BloodHound MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BloodHound MCP Server MCP server in PolicyLayer and add a rule for asset_groups: 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.
asset_groups is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the asset_groups 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 asset_groups. 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.
asset_groups 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.