playwright_click · Playwright MCP Server for Security MCP

WHAT IT DOES

What playwright_click does on Playwright MCP Server for Security

AI agents invoke playwright_click to trigger actions in Playwright MCP Server for Security. 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 playwright_click needs a policy

Clicking elements in a browser is an Execute-category action because its effects are entirely dependent on the target element and context. Clicking a button could submit forms, trigger purchases, delete data, navigate pages, or execute arbitrary application logic. In a security-focused server context, the blast radius is high as misuse could trigger unintended application actions.

From the tool's definition 'Click an element on the page' - triggers UI interactions that can cause navigation, form submissions, or other side effects depending on what is clicked

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

playwright_click Rate-limited

playwright_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": {
    "playwright_click": {
      "limits": [
        {
          "counter": "playwright_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 Playwright MCP Server for Security, so you can run agents against it safely.

FAQ

Questions about playwright_click

What does the playwright_click tool do? +

Click an element on the page. Supports both CSS selector and coordinate-based clicking for vision-based agents. It is categorised as a Execute tool in the Playwright MCP Server for Security MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on playwright_click? +

Register the Playwright MCP Server for Security MCP server in PolicyLayer and add a rule for playwright_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 Playwright MCP Server for Security. Nothing to install.

What risk level is playwright_click? +

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

Can I rate-limit playwright_click? +

Yes. Add a rate_limit block to the playwright_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 playwright_click completely? +

Set action: deny in the PolicyLayer policy for playwright_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 playwright_click? +

playwright_click is provided by the Playwright MCP Server for Security MCP server (o0x1024/mcp-playwright-security). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.