teammate_spawn · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What teammate_spawn does on Claude Flow

AI agents invoke teammate_spawn 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_spawn needs a policy

Spawning a new agent/teammate is an Execute-category action because it instantiates and starts a new running process or agent with its own execution context. Given this is part of an AI orchestration platform with 'hive-mind swarms' and code execution capabilities, a misused spawn could launch unauthorized agents performing arbitrary actions, making severity high.

From the tool's definition 'Spawn a new teammate in a team' — creates and launches a new agent/process instance; 'Returns AgentInput for Claude Code Task tool' indicates it triggers execution of an agent capable of running code tasks

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

teammate_spawn Rate-limited

teammate_spawn 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_spawn": {
      "limits": [
        {
          "counter": "teammate_spawn_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_spawn

What does the teammate_spawn tool do? +

Spawn a new teammate in a team. Returns AgentInput for Claude Code Task tool. 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_spawn? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for teammate_spawn: 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_spawn? +

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

Can I rate-limit teammate_spawn? +

Yes. Add a rate_limit block to the teammate_spawn 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_spawn completely? +

Set action: deny in the PolicyLayer policy for teammate_spawn. 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_spawn? +

teammate_spawn 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.