teammate_launch_swarm · Claude Flow MCP: Risk & Policy

WHAT IT DOES

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 IT NEEDS A POLICY

Why teammate_launch_swarm needs a policy

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

Recommended rule Ready

Verdict

teammate_launch_swarm Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "teammate_launch_swarm": {
      "limits": [
        {
          "counter": "teammate_launch_swarm_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about teammate_launch_swarm

What does the teammate_launch_swarm tool do? +

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.

How do I enforce a policy on teammate_launch_swarm? +

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.

What risk level is teammate_launch_swarm? +

teammate_launch_swarm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit teammate_launch_swarm? +

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.

How do I block teammate_launch_swarm completely? +

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.

What MCP server provides teammate_launch_swarm? +

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.