Get coordination metrics 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 call coordination_metrics to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves telemetry/monitoring data about agent coordination (voting, sync, load-balancing consensus). It is purely informational—an agent querying it observes system state without triggering side effects. The description explicitly contrasts it with task dispatch/orchestration (which would be Execute or Write), positioning it as a diagnostic/observability tool.
From the tool's definition Tool name includes 'metrics' and description states 'Get coordination metrics' — a retrieval operation. No data modification, deletion, execution of external code, or financial transaction occurs.
Attacks that exploit this kind of access
Get coordination metrics 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 Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for coordination_metrics: 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_metrics is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the coordination_metrics 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_metrics. 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_metrics 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.