Get the lifecycle state of a managed cloud-agent session: idle/running/error, title, last error. Use when native conversation memory is wrong because you need the cloud session\
AI agents call managed_agent_status to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about a managed agent session without modifying state, triggering actions, or affecting external systems. It is a pure query operation with negligible blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Get the lifecycle state' and lists read-only outputs: idle/running/error, title, last error. No mutations, side effects, or external operations.
Attacks that exploit this kind of access
Get the lifecycle state of a managed cloud-agent session: idle/running/error, title, last error. Use when native conversation memory is wrong because you need the cloud session\. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for managed_agent_status: 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_status 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 managed_agent_status 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_status. 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_status 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.