MCP Tool Reference High Risk

puppeteer_evaluate

Execute JavaScript in the browser console

Part of the Puppeteer MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

modelcontextprotocol/server-puppeteer Execute

WHEN AI AGENTS USE THIS TOOL

AI agents invoke puppeteer_evaluate to trigger processes or run actions in Puppeteer. Execute operations can have side effects beyond the immediate call — triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

WHY ENFORCE A POLICY ON PUPPETEER_EVALUATE

puppeteer_evaluate can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.

RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

puppeteer.yaml 
tools:
  puppeteer_evaluate:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full Puppeteer policy for all 7 tools.

DETAILS

Tool Name

puppeteer_evaluate

Category

Execute

MCP Server

Puppeteer MCP Server

Risk Level

High

MORE PUPPETEER TOOLS

puppeteer_click Other
Click elements on the page
puppeteer_fill Other
Fill out input fields
puppeteer_hover Other
Hover elements on the page
puppeteer_navigate Other
Navigate to any URL in the browser
puppeteer_screenshot Other
Capture screenshots of the entire page or specific elements
puppeteer_select Other
Select an element with SELECT tag

SIMILAR EXECUTE TOOLS ON OTHER SERVERS

call-actor Apify
Call an Actor and get its run results
boot_simulator Appium
Boot an iOS simulator
setup_wda Appium
Download and setup WebDriverAgent for iOS simulators
install_wda Appium
Install and launch WebDriverAgent on an iOS simulator
auth0_deploy_action Auth0
Deploy an Auth0 action
auth0_publish_form Auth0
Publish an Auth0 form

RELATED READING

FREQUENTLY ASKED QUESTIONS

What does the puppeteer_evaluate tool do?

Execute JavaScript in the browser console. 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_evaluate?

Add a rule in your Intercept YAML policy under the tools section for puppeteer_evaluate. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Puppeteer MCP server.

What risk level is puppeteer_evaluate?

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

Can I rate-limit puppeteer_evaluate?

Yes. Add a rate_limit block to the puppeteer_evaluate rule in your Intercept 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_evaluate completely?

Set action: deny in the Intercept policy for puppeteer_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_evaluate?

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

ENFORCE POLICIES ON PUPPETEER

Open source. One binary. Zero dependencies.

VIEW ON GITHUB Full Puppeteer policy →