Orchestrate multi-agent coordination Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine.
AI agents invoke coordination_orchestrate 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.
This tool executes coordination logic across multiple AI agents, triggering consensus protocols, synchronization, and load balancing. It is not merely reading or writing data — it actively drives agent behavior and dispatches work across a distributed system. Misuse could cause cascading effects across all orchestrated agents, leading to high blast radius.
From the tool's definition "Orchestrate multi-agent coordination" with agents that "vote/sync/load-balance" — triggers external operations across multiple agents
Attacks that exploit this kind of access
Orchestrate multi-agent coordination Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine. 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 coordination_orchestrate: 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.
coordination_orchestrate 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 coordination_orchestrate 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 coordination_orchestrate. 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.
coordination_orchestrate 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.