Create a new team for multi-agent collaboration using native TeammateTool.
AI agents use teammate_spawn_team to create or update resources in Claude Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
The tool creates a new team entity, which is a reversible write operation. It spawns a collaborative group of agents, which could have downstream resource implications, but the primary action is creation/configuration rather than execution of arbitrary code, destruction of data, or financial commitment.
From the tool's definition "Create a new team for multi-agent collaboration using native TeammateTool"
Attacks that exploit this kind of access
Create a new team for multi-agent collaboration using native TeammateTool. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for teammate_spawn_team: 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_spawn_team is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the teammate_spawn_team 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_spawn_team. 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_spawn_team 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.