Execute performance benchmarks (V2 compatible). Deprecated: Use system/metrics instead.
AI agents invoke benchmark_run 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 runs performance benchmarks, which triggers external operations whose effects depend on arguments (what benchmark to run, parameters, etc.). Although benchmarking is typically non-destructive, it qualifies as Execute rather than Read because it actively runs code/operations that consume resources and produce side effects (CPU/memory usage, I/O, timing measurements).
From the tool's definition Tool name 'benchmark_run' combined with description 'Execute performance benchmarks' explicitly indicates execution of code or operations. The term 'Execute' is the core verb in the description.
Attacks that exploit this kind of access
Execute performance benchmarks (V2 compatible). Deprecated: Use system/metrics instead. 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 benchmark_run: 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.
benchmark_run 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 benchmark_run 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 benchmark_run. 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.
benchmark_run 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.