AI agents invoke run_performance_audit to trigger actions in Browserless MCP Server. 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.
The tool executes a performance audit operation against a web resource, which qualifies as Execute rather than Read because it actively runs code/tools (Lighthouse) with effects determined by user-supplied arguments. While non-destructive and non-financial, it can consume significant resources, trigger rate limiting, or expose sensitive performance metrics about target systems.
From the tool's definition Tool performs 'Run Lighthouse performance audit' - executes an external operation (Lighthouse audit) whose effects depend on the target URL and audit parameters provided as arguments. This is a browser automation action that triggers external tools/services.
Documented attack patterns abuse exactly the kind of access run_performance_audit gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browserless MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_performance_audit:
{
"version": "1",
"default": "deny",
"tools": {
"run_performance_audit": {
"limits": [
{
"counter": "run_performance_audit_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_performance_audit stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run Lighthouse performance audit. It is categorised as a Execute tool in the Browserless MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browserless MCP Server MCP server in PolicyLayer and add a rule for run_performance_audit: 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 Browserless MCP Server. Nothing to install.
run_performance_audit 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 run_performance_audit 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 run_performance_audit. 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.
run_performance_audit is provided by the Browserless MCP Server MCP server (lizzard-solutions/browserless-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browserless MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 Browserless MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.