browser_stop · Daytona Playwright MCP Server MCP

WHAT IT DOES

What browser_stop does on Daytona Playwright MCP Server

AI agents invoke browser_stop to trigger actions in Daytona Playwright MCP 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 browser_stop needs a policy

While the tool does not delete persistent data or move money, stopping a browser and cleaning up a sandbox are Execute-class actions because they trigger external operations whose effects depend on execution context (the running Daytona instance). The cleanup aspect could be considered mildly destructive to the session, but the primary concern is execution of a process-termination command.

From the tool's definition The tool description states it will "Stop the browser and clean up the Daytona sandbox." This terminates a running process and performs cleanup operations on a cloud resource, which are external operations with irreversible effects on the browser session…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_stop Rate-limited

browser_stop 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": {
    "browser_stop": {
      "limits": [
        {
          "counter": "browser_stop_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 Daytona Playwright MCP Server, so you can run agents against it safely.

FAQ

Questions about browser_stop

What does the browser_stop tool do? +

Stop the browser and clean up the Daytona sandbox. It is categorised as a Execute tool in the Daytona Playwright MCP 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 browser_stop? +

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

What risk level is browser_stop? +

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

Can I rate-limit browser_stop? +

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

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

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