Take a screenshot of the current page for vision mode
AI agents call browser_vision_screen_capture to retrieve information from Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves visual information from the current browser page state. Screenshots are inherently non-destructive, non-financial, and do not modify data or trigger external operations. It is purely observational, similar to other Read category tools like 'browser_get_markdown' and 'browser_get_text' on the same server.
From the tool's definition Tool name 'browser_vision_screen_capture' and description 'Take a screenshot of the current page for vision mode' indicate a read-only operation that captures visual state without modifying data or executing commands.
Documented attack patterns abuse exactly the kind of access browser_vision_screen_capture gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_vision_screen_capture:
{
"version": "1",
"default": "deny",
"tools": {
"browser_vision_screen_capture": {}
}
}browser_vision_screen_capture 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 current page for vision mode. It is categorised as a Read tool in the Search MCP Server, which means it retrieves data without modifying state.
Register the Search MCP server in PolicyLayer and add a rule for browser_vision_screen_capture: 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 Search. Nothing to install.
browser_vision_screen_capture 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 browser_vision_screen_capture 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_vision_screen_capture. 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_vision_screen_capture is provided by the Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search, 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.
36 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.