click_by_role · Visual Annotation MCP: Risk & Policy

WHAT IT DOES

What click_by_role does on Visual Annotation MCP

AI agents invoke click_by_role 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_role needs a policy

This tool performs a browser click action on a UI element identified by its accessible role and optional name. Clicking can trigger form submissions, navigation, state changes, or other side effects depending on the target element, placing it firmly in the Execute category. Misuse could cause unintended actions in a web application.

From the tool's definition Click by accessible role and optional name — triggers a click action on a web page element

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

click_by_role Rate-limited

click_by_role 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_role": {
      "limits": [
        {
          "counter": "click_by_role_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_role

What does the click_by_role tool do? +

Click by accessible role and optional name. 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_role? +

Register the Visual Annotation MCP server in PolicyLayer and add a rule for click_by_role: 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_role? +

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

Can I rate-limit click_by_role? +

Yes. Add a rate_limit block to the click_by_role 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_role completely? +

Set action: deny in the PolicyLayer policy for click_by_role. 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_role? +

click_by_role 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.