Generate performance report Use when native shell timing (
AI agents call performance_report 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.
The tool generates a performance report, which is a read/query operation that collects and presents timing and metrics data without modifying or deleting anything. The description is truncated ('Use when native shell timing ('), which slightly lowers confidence, but the core action is reporting/reading. Severity is low as misuse would at most expose performance data.
From the tool's definition 'Generate performance report' — reads and aggregates performance metrics/timing data into a report
Attacks that exploit this kind of access
Generate performance report Use when native shell timing (. 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 performance_report: 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.
performance_report 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 performance_report 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 performance_report. 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.
performance_report 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.