Execute Playwright code in the browser. This tool runs JavaScript code with access to a Playwright page object. The browser session persists across calls, so you can navigate, interact with elements, and extract data across multiple tool invocations. Available in scope: - page - The Playwright Pa...
Risk signalsAccepts freeform code/query input (code)
Part of the Playwright Stealth server.
Free to start. No card required.
AI agents invoke browser_execute to trigger processes or run actions in Playwright Stealth. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
browser_execute can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"browser_execute": {
"limits": [
{
"counter": "browser_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Playwright Stealth policy for all 6 tools.
These attack patterns abuse exactly the kind of access browser_execute gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Execute Playwright code in the browser. This tool runs JavaScript code with access to a Playwright page object. The browser session persists across calls, so you can navigate, interact with elements, and extract data across multiple tool invocations. Available in scope: - page - The Playwright Page object with full API access Example usage: Navigate to a page: javascript await page.goto('https://example.com'); return await page.title(); Click an element and wait: javascript await page.click('button.submit'); await page.waitForSelector('.success-message'); Extract text content: javascript const items = await page.$$eval('.item', els => els.map(el => el.textContent)); return items; Fill a form: javascript await page.fill('input[name="email"]', 'test@example.com'); await page.fill('input[name="password"]', 'secret'); await page.click('button[type="submit"]'); Returns: - success: boolean indicating if execution succeeded - result: JSON stringified return value (if any) - error: error message (if failed) - consoleOutput: array of console messages from the page Note: When STEALTH_MODE=true, the browser includes anti-detection measures to help bypass bot protection.. It is categorised as a Execute tool in the Playwright Stealth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright Stealth MCP server in PolicyLayer and add a rule for browser_execute: 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 Playwright Stealth. Nothing to install.
browser_execute 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_execute 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_execute. 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_execute is provided by the Playwright Stealth MCP server (pulsemcp/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Playwright Stealth tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.