browse_evaluate
Run JavaScript in the current page and return its result — powerful: extract complex data or drive JS widgets the @eN/CSS verbs can't. Runs in the page's sandbox (not the host); navigation stays SSRF-guarded.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-evaluate.md
What browse_evaluate does on Gateway
AI agents invoke browse_evaluate to trigger actions in Gateway. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
js | string | Yes | JavaScript expression/IIFE to evaluate in the page |
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_evaluate is rated High
This tool executes arbitrary JavaScript in a page context. While it's sandboxed to the page and SSRF-guarded for navigation, running arbitrary JS can exfiltrate data, manipulate page state, trigger network requests, and cause wide-ranging effects depending on arguments.
From the tool's definition 'Run JavaScript in the current page and return its result' and 'drive JS widgets' — explicitly executes arbitrary JavaScript code
Risk signalsAccepts freeform code/query input (js)
Attacks that exploit this kind of access
The rule that runs browse_evaluate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browse_evaluate, this is the rule to start with:
browse_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every browse_evaluate call is checked against it from then on.
Questions about browse_evaluate
Run JavaScript in the current page and return its result — powerful: extract complex data or drive JS widgets the @eN/CSS verbs can't. Runs in the page's sandbox (not the host); navigation stays SSRF-guarded. It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browse_evaluate accepts 2 parameters: js, browser_id. Required: js, browser_id. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for browse_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 Gateway. Nothing to install.
browse_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 browse_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 browse_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.
browse_evaluate is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
Across the catalogue