click_by_selector · Visual Annotation MCP: Risk & Policy

WHAT IT DOES

What click_by_selector does on Visual Annotation MCP

AI agents invoke click_by_selector to trigger actions in Visual Annotation MCP. 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_by_selector needs a policy

Clicking UI elements is a browser action that can trigger external operations (form submissions, navigation, purchases, deletions) depending on which element is targeted. The effect is determined by arguments, making this an Execute-category tool with high severity due to the wide range of potentially irreversible or impactful actions a click can initiate.

From the tool's definition 'Click the first element matching a CSS selector' — triggers a browser click action on an arbitrary DOM element

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

click_by_selector Rate-limited

click_by_selector 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_by_selector": {
      "limits": [
        {
          "counter": "click_by_selector_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 Visual Annotation MCP, so you can run agents against it safely.

FAQ

Questions about click_by_selector

What does the click_by_selector tool do? +

Click the first element matching a CSS selector. It is categorised as a Execute tool in the Visual Annotation MCP 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_by_selector? +

Register the Visual Annotation MCP server in PolicyLayer and add a rule for click_by_selector: 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 Visual Annotation MCP. Nothing to install.

What risk level is click_by_selector? +

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

Can I rate-limit click_by_selector? +

Yes. Add a rate_limit block to the click_by_selector 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_by_selector completely? +

Set action: deny in the PolicyLayer policy for click_by_selector. 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_by_selector? +

click_by_selector is provided by the Visual Annotation MCP server (mstocker1/visual_annotation_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

click_by_selector is one line of Visual Annotation's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →