Take a screenshot of the bound page. Saves to file_path if provided; otherwise reports byte count without embedding the image.
AI agents call interceptor_browser_screenshot to retrieve information from Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a read-only operation that retrieves the current visual state of a page. While screenshots can reveal sensitive information displayed on screen, the tool itself performs no side effects—it does not modify, execute, or destroy data. The severity is low because the tool is constrained to passive observation of an already-bound page and does not trigger further actions or system-level operations.
From the tool's definition The tool takes a screenshot of a bound page and 'reports byte count without embedding the image' or 'saves to file_path if provided'. It retrieves visual data from a page with no modification, deletion, or execution of code.
Documented attack patterns abuse exactly the kind of access interceptor_browser_screenshot 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_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"interceptor_browser_screenshot": {}
}
}interceptor_browser_screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Take a screenshot of the bound page. Saves to file_path if provided; otherwise reports byte count without embedding the image. It is categorised as a Read tool in the Proxy MCP Server, which means it retrieves data without modifying state.
Register the Proxy MCP server in PolicyLayer and add a rule for interceptor_browser_screenshot: 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_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the interceptor_browser_screenshot 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_screenshot. 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_screenshot 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.