click_element_by_selector

THE RISK

High Risk

Why click_element_by_selector needs a policy

This tool performs click/press actions on UI elements in macOS applications. Clicking UI elements can trigger arbitrary application behaviors—submitting forms, deleting files, confirming dialogs, launching processes—making it an Execute-category tool with high severity since an AI agent could interact with any UI element across any running application, potentially causing significant unintended consequences.

From the tool's definition Click a UI element using accessibility actions (AXPress) via JSONPath selector

Documented attack patterns abuse exactly the kind of access click_element_by_selector gives an agent:

POLICY

How to control click_element_by_selector

PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP for macOS, and nothing reaches the server without passing your rules. This is the rule we recommend for click_element_by_selector:

policy.json

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

click_element_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.

Create a free account and register Playwright MCP for macOS — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Playwright MCP for macOS tools

Execute click_at_position Click at a specific screen position using coordinates. Write type_text_to_element_by_selector Type text into a UI element using JSONPath selector. Read check_accessibility_permissions Check if accessibility permissions are properly configured. Read find_elements Find UI elements matching a JSONPath selector. Read find_elements_in_app find_elements_in_app Read get_app_overview Get a quick overview of all running applications with shallow UI inspection. Read get_element_details Get detailed information about a specific UI element. Read list_running_applications List all currently running applications with basic info.

All 9 Playwright MCP for macOS tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Playwright MCP for macOS → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about click_element_by_selector

What does the click_element_by_selector tool do? +

Click a UI element using accessibility actions (AXPress) via JSONPath selector. It is categorised as a Execute tool in the Playwright MCP for macOS 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_element_by_selector? +

Register the Playwright MCP for macOS MCP server in PolicyLayer and add a rule for click_element_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 Playwright MCP for macOS. Nothing to install.

What risk level is click_element_by_selector? +

click_element_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_element_by_selector? +

Yes. Add a rate_limit block to the click_element_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_element_by_selector completely? +

Set action: deny in the PolicyLayer policy for click_element_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_element_by_selector? +

click_element_by_selector is provided by the Playwright MCP for macOS MCP server (mb-dev/macos-ui-automation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Playwright MCP for macOS tool call.

Start from Playwright MCP for macOS, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →