frame_action · MCP Playwright Server MCP: Risk & Policy

WHAT IT DOES

What frame_action does on MCP Playwright Server

AI agents invoke frame_action to trigger actions in MCP Playwright Server. 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 frame_action needs a policy

This tool performs browser interactions (click, fill) inside iframes, which can trigger form submissions, navigate pages, modify web application state, or exfiltrate data. 'click' and 'fill' are active operations with real-world side effects that depend on the target element and context, placing this firmly in Execute. Misuse by an AI agent could trigger unintended actions on arbitrary web pages.

From the tool's definition Perform an action (click, fill, getText, waitForSelector) inside an iframe

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

frame_action Rate-limited

frame_action 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": {
    "frame_action": {
      "limits": [
        {
          "counter": "frame_action_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 MCP Playwright Server, so you can run agents against it safely.

FAQ

Questions about frame_action

What does the frame_action tool do? +

Perform an action (click, fill, getText, waitForSelector) inside an iframe. It is categorised as a Execute tool in the MCP Playwright Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on frame_action? +

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

What risk level is frame_action? +

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

Can I rate-limit frame_action? +

Yes. Add a rate_limit block to the frame_action 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 frame_action completely? +

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

frame_action is provided by the MCP Playwright Server MCP server (j0hanz/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.