Evaluate JavaScript expression on page or element and return result
AI agents invoke browser_evaluate to trigger actions in Fast 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 executes arbitrary JavaScript in the browser page context, which can perform any action including DOM manipulation, network requests, data exfiltration, or triggering destructive operations. The blast radius is high because arbitrary JS execution grants broad capabilities limited only by browser sandbox.
From the tool's definition "Evaluate JavaScript expression on page or element and return result"
Documented attack patterns abuse exactly the kind of access browser_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fast Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"browser_evaluate": {
"limits": [
{
"counter": "browser_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_evaluate 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.
Evaluate JavaScript expression on page or element and return result. It is categorised as a Execute tool in the Fast Playwright MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fast Playwright MCP server in PolicyLayer and add a rule for browser_evaluate: 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 Fast Playwright MCP. Nothing to install.
browser_evaluate 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_evaluate 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_evaluate. 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_evaluate is provided by the Fast Playwright MCP server (tontoko/fast-playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 34 Fast Playwright MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
34 Fast Playwright MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.