Teleport team to a new context/working directory
AI agents invoke teammate_teleport 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.
Changing the working directory or operational context for an agent team triggers an external state transition that affects subsequent operations. This is an Execute-class action since it alters runtime environment state for potentially many agents simultaneously.
From the tool's definition 'Teleport team to a new context/working directory' — changes the working directory/context for a team of agents
Attacks that exploit this kind of access
Teleport team to a new context/working directory. 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_teleport: 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_teleport 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_teleport 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_teleport. 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_teleport 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.