Remove members from a role
AI agents call remove_role_members to permanently remove resources in HAP MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing members from a role strips their permissions and access rights. This is effectively irreversible without knowing the prior state, as the system likely doesn't automatically restore membership. The blast radius is high because an AI agent misusing this tool could remove legitimate users from critical roles, causing loss of access across the platform.
From the tool's definition 'Remove members from a role' - removing members is an irreversible action that revokes access/permissions
Attacks that exploit this kind of access
Remove members from a role. It is categorised as a Destructive tool in the HAP MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the HAP MCP Server MCP server in PolicyLayer and add a rule for remove_role_members: 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 HAP MCP Server. Nothing to install.
remove_role_members 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 remove_role_members 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 remove_role_members. 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.
remove_role_members is provided by the HAP MCP Server MCP server (mingdaocloud/hap-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →