browser_click_at · MCProxy MCP: Risk & Policy

WHAT IT DOES

What browser_click_at does on MCProxy

AI agents invoke browser_click_at to trigger actions in MCProxy. 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.

WHY IT NEEDS A POLICY

Why browser_click_at needs a policy

Clicking at coordinates in a controlled browser can execute any action visible on screen: submitting payments, confirming deletions, navigating, logging in, etc. The effect is entirely context-dependent and can span from benign to financial or destructive, making Execute the correct base category with high severity given the headless browser context and potential for misuse across arbitrary web pages.

From the tool's definition 'Click at specific coordinates on the page' — triggers browser interaction at arbitrary coordinates, which can activate UI elements, submit forms, navigate pages, or trigger external operations depending on what is rendered.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_click_at Rate-limited

browser_click_at 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_click_at": {
      "limits": [
        {
          "counter": "browser_click_at_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCProxy, so you can run agents against it safely.

FAQ

Questions about browser_click_at

What does the browser_click_at tool do? +

Click at specific coordinates on the page. Coordinates are RELATIVE (0-1 range): x=0 is left edge, x=1 is right edge, y=0 is top, y=1 is bottom. Use this when you can see a screenshot and want to click a specific location. It is categorised as a Execute tool in the MCProxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_click_at? +

Register the MCProxy MCP server in PolicyLayer and add a rule for browser_click_at: 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 MCProxy. Nothing to install.

What risk level is browser_click_at? +

browser_click_at is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_click_at? +

Yes. Add a rate_limit block to the browser_click_at 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.

How do I block browser_click_at completely? +

Set action: deny in the PolicyLayer policy for browser_click_at. 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.

What MCP server provides browser_click_at? +

browser_click_at is provided by the MCProxy MCP server (saladtechnologies/mcproxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.