puppeteer_devtools_evaluate · MCP-pptr MCP: Risk & Policy

WHAT IT DOES

What puppeteer_devtools_evaluate does on MCP-pptr

AI agents invoke puppeteer_devtools_evaluate to trigger actions in MCP-pptr. 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_devtools_evaluate needs a policy

Chrome DevTools Protocol commands are powerful execution primitives that can perform code execution, inspect and modify page state, trigger network requests, and interact with browser internals.

From the tool's definition Tool description states 'Execute CDP command' — this directly invokes Chrome DevTools Protocol commands, which can run arbitrary operations in a browser context including JavaScript execution, network manipulation, and DOM inspection/modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_devtools_evaluate Rate-limited

puppeteer_devtools_evaluate 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_devtools_evaluate": {
      "limits": [
        {
          "counter": "puppeteer_devtools_evaluate_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-pptr, so you can run agents against it safely.

FAQ

Questions about puppeteer_devtools_evaluate

What does the puppeteer_devtools_evaluate tool do? +

Execute CDP command. It is categorised as a Execute tool in the MCP-pptr 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_devtools_evaluate? +

Register the MCP-pptr MCP server in PolicyLayer and add a rule for puppeteer_devtools_evaluate: 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-pptr. Nothing to install.

What risk level is puppeteer_devtools_evaluate? +

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

Can I rate-limit puppeteer_devtools_evaluate? +

Yes. Add a rate_limit block to the puppeteer_devtools_evaluate 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_devtools_evaluate completely? +

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

puppeteer_devtools_evaluate is provided by the MCP-pptr MCP server (ringotc/mcp-pptr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

puppeteer_devtools_evaluate is one line of MCP-pptr's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →