managed_agent_create
Spin up an Anthropic-managed cloud agent (Agent + Environment + Session) — the CLOUD counterpart of wasm_agent_create. Use when wasm_agent_create (local WASM sandbox) is wrong because the task is long-running/async (minutes-hours), needs a real cloud container with pre-installed packages + networ...
This record as markdown: /tools/io-github-ruvnet-claude-flow/managed-agent-create.md
What managed_agent_create does on Claude Flow
AI agents invoke managed_agent_create 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.
Why managed_agent_create is rated High
This tool provisions and launches a cloud-hosted agent environment with network access, persistent filesystem, and container execution capabilities. It triggers external infrastructure operations (cloud container + session creation) whose effects depend on arguments, and the spawned agent can execute arbitrary tasks over minutes to hours.
From the tool's definition Spin up an Anthropic-managed cloud agent (Agent + Environment + Session)... needs a real cloud container with pre-installed packages + network, or persistent filesystem + transcript across turns
Attacks that exploit this kind of access
The rule that runs managed_agent_create safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For managed_agent_create, this is the rule to start with:
managed_agent_create stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every managed_agent_create call is checked against it from then on.
Questions about managed_agent_create
Spin up an Anthropic-managed cloud agent (Agent + Environment + Session) — the CLOUD counterpart of wasm_agent_create. Use when wasm_agent_create (local WASM sandbox) is wrong because the task is long-running/async (minutes-hours), needs a real cloud container with pre-installed packages + network, or persistent filesystem + transcript across turns. For a fast, free, ephemeral, offline agent use wasm_agent_create (rvagent). Needs ANTHROPIC_API_KEY + Managed Agents beta access. Returns {sessionId, agentId, environmentId}; pair with managed_agent_prompt. 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_create: 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_create 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_create 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_create. 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_create 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.
More on Claude Flow, and thousands of servers like it.
Across the catalogue