Run arbitrary JS in the page/frame context. Disabled by default; enable with MCP_ALLOW_EVALUATE=true.
AI agents invoke browser.evaluate to trigger actions in MCP Playwright Browser. 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 enables unrestricted execution of arbitrary JavaScript in the page context, which can read/modify DOM, exfiltrate data, perform actions on behalf of the user, redirect to malicious sites, or interact with any web service the page has access to. The blast radius is critical because an AI agent could inadvertently execute malicious or unintended code.
From the tool's definition "Run arbitrary JS in the page/frame context" - the tool explicitly allows execution of arbitrary JavaScript code within the browser context.
Attacks that exploit this kind of access
Run arbitrary JS in the page/frame context. Disabled by default; enable with MCP_ALLOW_EVALUATE=true. It is categorised as a Execute tool in the MCP Playwright Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Playwright Browser 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 MCP Playwright Browser. 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 MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
browser.evaluate is one line of MCP Playwright Browser's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →