AI agents call onprem_users_group_entra_roles to retrieve information from BloodHound MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
BloodHound is a security analysis tool used for querying Active Directory/Entra relationships. This tool follows the pattern of other sibling tools which retrieve security-relevant information without modifying data. The pattern 'onprem_users_group_[by]_entra_roles' indicates grouping and retrieving user data by role assignment—a pure query/retrieval operation.
From the tool's definition Tool name 'onprem_users_group_entra_roles' suggests querying/retrieving users grouped by their Entra roles.
Documented attack patterns abuse exactly the kind of access onprem_users_group_entra_roles gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BloodHound MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for onprem_users_group_entra_roles:
{
"version": "1",
"default": "deny",
"tools": {
"onprem_users_group_entra_roles": {}
}
}onprem_users_group_entra_roles 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.
onprem_users_group_entra_roles. It is categorised as a Read tool in the BloodHound MCP MCP Server, which means it retrieves data without modifying state.
Register the BloodHound MCP server in PolicyLayer and add a rule for onprem_users_group_entra_roles: 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. Nothing to install.
onprem_users_group_entra_roles 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 onprem_users_group_entra_roles 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 onprem_users_group_entra_roles. 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.
onprem_users_group_entra_roles is provided by the BloodHound MCP server (mordavid/bloodhound-mcp-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BloodHound MCP, 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.
75 BloodHound MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.