AI agents call browser_perf_stop_coverage to retrieve information from Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool stops a coverage session and retrieves results about code usage. It reads/collects diagnostic data about which code was executed versus unused. While it does stop a running process, the primary effect is returning data with no meaningful side effects on external state. Severity is low as misuse would only result in coverage data collection being terminated prematurely.
From the tool's definition Stop coverage and get results showing used vs unused code
Attacks that exploit this kind of access
Stop coverage and get results showing used vs unused code (see browser_docs). It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for browser_perf_stop_coverage: 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 Browser. Nothing to install.
browser_perf_stop_coverage 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 browser_perf_stop_coverage 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 browser_perf_stop_coverage. 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.
browser_perf_stop_coverage is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →