click · Pl MCP: Risk & Policy

WHAT IT DOES

What click does on Pl

AI agents invoke click to trigger actions in Pl. 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 click needs a policy

Clicking a UI element is an external operation whose consequences are highly context-dependent. An AI agent could click 'Delete', 'Confirm Payment', or any other button, making this a high-severity Execute action. The blast radius is high because click actions can chain into Destructive or Financial operations depending on the target element.

From the tool's definition 'Click at coordinates (x, y) in the application window' — triggers UI interactions whose effects depend entirely on what element is clicked, ranging from benign navigation to destructive or financial actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

click Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "click": {
      "limits": [
        {
          "counter": "click_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 Pl, so you can run agents against it safely.

FAQ

Questions about click

What does the click tool do? +

Click at coordinates (x, y) in the application window. Use capture_screenshot to find element positions. It is categorised as a Execute tool in the Pl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on click? +

Register the Pl 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 Pl. Nothing to install.

What risk level is click? +

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

Can I rate-limit click? +

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.

How do I block click completely? +

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.

What MCP server provides click? +

click is provided by the Pl MCP server (@milaboratories/pl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.