Click left mouse button on the page with vision and snapshot, before calling this tool, you should call
AI agents invoke browser_vision_screen_click to trigger actions in Search. 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 executes a mouse click action on a web page, which triggers external operations whose effects depend on what is clicked. Clicking can submit forms, trigger purchases, navigate pages, or cause other side effects. This is an Execute-category action with high severity since an AI agent could misuse it to interact with arbitrary web page elements, potentially causing unintended consequences.
From the tool's definition 'Click left mouse button on the page with vision and snapshot' — performs an interactive click action on a web page
Documented attack patterns abuse exactly the kind of access browser_vision_screen_click 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_click:
{
"version": "1",
"default": "deny",
"tools": {
"browser_vision_screen_click": {
"limits": [
{
"counter": "browser_vision_screen_click_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_vision_screen_click 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.
Click left mouse button on the page with vision and snapshot, before calling this tool, you should call. It is categorised as a Execute tool in the Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Search MCP server in PolicyLayer and add a rule for browser_vision_screen_click: 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_click 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_vision_screen_click 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_click. 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_click 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.