Get collected metrics
AI agents call get-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 queries existing metrics data. It has no capability to modify, delete, execute external operations, or move financial resources. The read-only nature and presence among other agent monitoring tools confirm this is a safe data retrieval operation. Low severity reflects minimal blast radius if misused—an agent could only retrieve potentially sensitive performance data, not alter system state.
From the tool's definition Tool name 'get-metrics' and description 'Get collected metrics' indicate data retrieval with no modification or side effects. Consistent with sibling tools like 'agent_metrics' and 'agent_health' which are monitoring/observability functions.
Attacks that exploit this kind of access
Get collected metrics. 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 get-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.
get-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 get-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 get-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.
get-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.