AI agents call performance_bottleneck to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool description is truncated and uninformative beyond 'Detect performance bottlenecks Use when native shell timing ('. The primary action described is detection/analysis, which is a read/query operation. However, given the context of a multi-agent harness with shell integration, there's some possibility it could execute shell commands to gather timing data.
From the tool's definition Detect performance bottlenecks - the tool appears to analyze and report on performance issues
Attacks that exploit this kind of access
Detect performance bottlenecks Use when native shell timing (. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for performance_bottleneck: 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 Ruflo. Nothing to install.
performance_bottleneck 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_bottleneck 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_bottleneck. 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_bottleneck is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
performance_bottleneck is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →