Remove an agent/member from the live roster while preserving message and task history.
AI agents call remove_agent to permanently remove resources in Agent Bus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing an agent from the live roster is an irreversible action that affects system state — the agent is taken off the active roster. While message and task history is preserved, the removal of the agent itself cannot be undone without re-registering, making this Destructive. Blast radius is medium as it could disrupt ongoing collaborations or task assignments involving that agent.
From the tool's definition Remove an agent/member from the live roster
Attacks that exploit this kind of access
Remove an agent/member from the live roster while preserving message and task history. It is categorised as a Destructive tool in the Agent Bus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Bus MCP server in PolicyLayer and add a rule for remove_agent: 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 Agent Bus. Nothing to install.
remove_agent 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_agent 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_agent. 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_agent is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →