Perform a task with the browser. It can click, type, export, capture screenshot, drag, hover, select options, etc.
AI agents invoke browser_perform to trigger actions in Better Playwright MCP. 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 triggers a broad range of browser actions (clicks, typing, dragging, exports, etc.) whose effects depend entirely on the arguments passed. It can interact with any web content, submit forms, trigger downloads, or invoke arbitrary web operations — making it an Execute-category tool with high blast radius since an AI agent could misuse it to perform unintended web interactions across any site.
From the tool's definition 'Perform a task with the browser. It can click, type, export, capture screenshot, drag, hover, select options, etc.'
Documented attack patterns abuse exactly the kind of access browser_perform gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Better Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_perform:
{
"version": "1",
"default": "deny",
"tools": {
"browser_perform": {
"limits": [
{
"counter": "browser_perform_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_perform 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.
Perform a task with the browser. It can click, type, export, capture screenshot, drag, hover, select options, etc. It is categorised as a Execute tool in the Better Playwright MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Better Playwright MCP server in PolicyLayer and add a rule for browser_perform: 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 Better Playwright MCP. Nothing to install.
browser_perform 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 browser_perform 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_perform. 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_perform is provided by the Better Playwright MCP server (livoras/better-playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Better Playwright MCP, 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.
29 Better Playwright MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.