View learning metrics dashboard Use when native Bash hooks (via Claude Code\
AI agents call hooks_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 and displays metrics data from a dashboard—a read-only operation with no side effects. The 'View' verb and 'dashboard' context confirm it queries existing telemetry/monitoring information rather than executing code, modifying state, or triggering external operations.
From the tool's definition Tool name 'hooks_metrics' and description 'View learning metrics dashboard' indicate retrieval/display of monitoring data with no modification or execution capability.
Attacks that exploit this kind of access
View learning metrics dashboard Use when native Bash hooks (via Claude Code\. 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 hooks_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.
hooks_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 hooks_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 hooks_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.
hooks_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.