Send a user turn to a managed cloud-agent session and wait for it to go idle, returning the assistant text + a tool-use trace — the CLOUD counterpart of wasm_agent_prompt. Use when wasm_agent_prompt (local WASM) is wrong because the work is long-running, needs the cloud container, or must persist...
AI agents invoke managed_agent_prompt to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends prompts to a live cloud-hosted AI agent session and waits for it to complete work. The agent can use tools itself (evidenced by 'tool-use trace'), meaning arbitrary downstream actions can be triggered depending on arguments. This is a classic Execute pattern — it runs external operations in a cloud container whose effects depend on the prompt provided.
From the tool's definition "Send a user turn to a managed cloud-agent session and wait for it to go idle" and "the CLOUD counterpart of wasm_agent_prompt" — triggers execution of an AI agent session in a cloud container
Attacks that exploit this kind of access
Send a user turn to a managed cloud-agent session and wait for it to go idle, returning the assistant text + a tool-use trace — the CLOUD counterpart of wasm_agent_prompt. Use when wasm_agent_prompt (local WASM) is wrong because the work is long-running, needs the cloud container, or must persist across turns. Polls the session event log up to maxWaitMs (default 180s); for very long tasks raise maxWaitMs or follow up with managed_agent_events. Pair with managed_agent_create (for sessionId). It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for managed_agent_prompt: 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_prompt is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the managed_agent_prompt 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_prompt. 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_prompt 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.