This record as markdown: /tools/io-github-ruvnet-claude-flow/teammate-launch-swarm.md
What teammate_launch_swarm does on Claude Flow
AI agents invoke teammate_launch_swarm 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 teammate_launch_swarm is rated High
This tool triggers execution of a swarm (distributed agents) to carry out a plan. The blast radius is significant: swarms can perform multiple concurrent operations, and if a plan is malformed or adversarially crafted, the swarm could execute unintended actions across multiple systems. However, the mention of 'approved plan' suggests some guardrails exist, preventing a critical rating.
From the tool's definition Tool name contains 'launch' and description states 'execute an approved plan' — launching a swarm indicates triggering external operations with effects dependent on the plan argument.
Attacks that exploit this kind of access
The rule that runs teammate_launch_swarm 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 teammate_launch_swarm, this is the rule to start with:
teammate_launch_swarm 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 teammate_launch_swarm call is checked against it from then on.
Questions about teammate_launch_swarm
Launch swarm to execute an approved plan. 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 teammate_launch_swarm: 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.
teammate_launch_swarm 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 teammate_launch_swarm 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 teammate_launch_swarm. 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.
teammate_launch_swarm 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