Delete a managed cloud-agent session (stops billing for it) — the CLOUD counterpart of wasm_agent_terminate. Use when native nothing applies because a cloud session keeps billing container time + tokens until deleted. For a local WASM agent use wasm_agent_terminate. Optionally also deletes the se...
AI agents call managed_agent_terminate to permanently remove resources in Claude Flow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a cloud-agent session, which is an irreversible action (termination of a running agent and destruction of its session state). It also has financial implications by stopping billing, but the primary action is destructive — deleting the session.
From the tool's definition 'Delete a managed cloud-agent session' and 'Optionally also deletes the session' — the tool terminates and deletes a cloud agent session irreversibly
Attacks that exploit this kind of access
Delete a managed cloud-agent session (stops billing for it) — the CLOUD counterpart of wasm_agent_terminate. Use when native nothing applies because a cloud session keeps billing container time + tokens until deleted. For a local WASM agent use wasm_agent_terminate. Optionally also deletes the session\. It is categorised as a Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow MCP server in PolicyLayer and add a rule for managed_agent_terminate: 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 Claude Flow. Nothing to install.
managed_agent_terminate 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 managed_agent_terminate 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 managed_agent_terminate. 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.
managed_agent_terminate is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.