Execute a JS file in the page and return its result.
AI agents invoke interceptor_browser_evaluate to trigger actions in Proxy. 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 is clearly an Execute tool—it runs code (JavaScript) in a real browser environment with full access to that context. The critical severity reflects the extreme blast radius: arbitrary JS execution in a browser can exfiltrate sensitive data, manipulate finances, perform actions on behalf of the user, or compromise connected systems.
From the tool's definition Execute a JS file in the page and return its result. This directly runs arbitrary JavaScript within a browser context, which can access/modify page state, steal credentials, perform actions as the user, and interact with any resources the page has access to.
Documented attack patterns abuse exactly the kind of access interceptor_browser_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for interceptor_browser_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"interceptor_browser_evaluate": {
"limits": [
{
"counter": "interceptor_browser_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}interceptor_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.
Execute a JS file in the page and return its result. It is categorised as a Execute tool in the Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Proxy MCP server in PolicyLayer and add a rule for interceptor_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 Proxy. Nothing to install.
interceptor_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 interceptor_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 interceptor_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.
interceptor_browser_evaluate is provided by the Proxy MCP server (yfe404/proxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Proxy, 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.
89 Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.