puppeteer_select · Puppeteer MCP: Risk & Policy

WHAT IT DOES

What puppeteer_select does on Puppeteer

AI agents invoke puppeteer_select to trigger actions in Puppeteer. 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 puppeteer_select needs a policy

Puppeteer tools perform browser automation actions. 'puppeteer_select' almost certainly selects an option in a dropdown or form element, which is a browser action/interaction (Execute category). Sibling tools confirm this is a browser automation server. Empty description lowers confidence slightly, but the naming pattern and context strongly suggest an interactive browser action.

From the tool's definition Tool name 'puppeteer_select' on a Puppeteer server with sibling tools including puppeteer_click, puppeteer_evaluate, puppeteer_fill, puppeteer_navigate — all browser automation/execution tools. Description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_select Rate-limited

puppeteer_select 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": {
    "puppeteer_select": {
      "limits": [
        {
          "counter": "puppeteer_select_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 Puppeteer, so you can run agents against it safely.

FAQ

Questions about puppeteer_select

What does the puppeteer_select tool do? +

puppeteer_select. It is categorised as a Execute tool in the Puppeteer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on puppeteer_select? +

Register the Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_select: 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 Puppeteer. Nothing to install.

What risk level is puppeteer_select? +

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

Can I rate-limit puppeteer_select? +

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

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

puppeteer_select is provided by the Puppeteer MCP server (@modelcontextprotocol/server-puppeteer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.