Click at specific x,y coordinates in the browser window. IMPORTANT: Always check the page info after clicking. When interacting with dropdowns, use ArrowUp and ArrowDown keys. Try to figure out what the selected item is when interacting with the dropdowns and use that to navigate.
AI agents invoke click to trigger actions in Chrome MCP Server. 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.
Clicking in a browser can trigger arbitrary actions: form submissions, purchases, downloads, navigation, authentication flows, etc. The effect is entirely argument-dependent and can span multiple risk categories. Execute is appropriate as the most accurate base category, with high severity due to the broad blast radius of uncontrolled browser clicks by an AI agent.
From the tool's definition 'Click at specific x,y coordinates in the browser window' — triggers browser UI interactions via Chrome DevTools Protocol, causing navigation, form submissions, button activations, or other side effects depending on what is clicked.
Documented attack patterns abuse exactly the kind of access click gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for click:
{
"version": "1",
"default": "deny",
"tools": {
"click": {
"limits": [
{
"counter": "click_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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 at specific x,y coordinates in the browser window. IMPORTANT: Always check the page info after clicking. When interacting with dropdowns, use ArrowUp and ArrowDown keys. Try to figure out what the selected item is when interacting with the dropdowns and use that to navigate. It is categorised as a Execute tool in the Chrome MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for 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 Chrome MCP Server. Nothing to install.
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 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 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.
click is provided by the Chrome MCP Server MCP server (lxe/chrome-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Chrome MCP Server, 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.
11 Chrome MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.