done

THE RISK

Low Risk

Why done needs a policy

This tool appears to be a terminal/completion signal that marks a task as done. It does not read, write, execute, destroy, or move money — it merely signals task completion. The description is minimal, which lowers confidence slightly, but there is no indication of any side effects.

From the tool's definition Call this tool when the task is complete.

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

POLICY

How to control done

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "done": {
      "limits": [
        {
          "counter": "done_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

done gets a rate cap, and everything else on the server is denied unless you say otherwise.

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

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Better Playwright MCP tools

Destructive browser_close Close the page Execute browser_navigate Navigate to a URL Execute browser_navigate_back Go back to the previous page Execute browser_wait_for Wait for text to appear or disappear or a specified time to pass Execute browser_click Perform click on a web page Execute browser_drag Perform drag and drop between two elements Execute browser_evaluate Evaluate JavaScript expression on page or element Execute browser_fill_form Fill multiple form fields

All 29 Better Playwright MCP tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about done

What does the done tool do? +

Call this tool when the task is complete. It is categorised as a Other tool in the Better Playwright MCP MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on done? +

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

What risk level is done? +

done is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit done? +

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

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

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

Enforce policy on every Better Playwright MCP tool call.

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

CHECK YOUR STACK →