DEV Community

Manuel Bruña
Manuel Bruña

Posted on

Safer browser automation with a Puppeteer MCP server

Browser automation is one of the most useful abilities for AI agents.

It is also one of the easiest places to make a mess.

A browser tool can click, fill forms, run JavaScript, capture pages and move through real user flows. That power needs boundaries.

That is why I built a Puppeteer MCP server with safety controls in mind.

Repo:
https://github.com/tecnomanu/puppeteer-server

What it supports:

  • real browser navigation
  • screenshots
  • element clicks
  • form filling
  • JavaScript evaluation
  • console log capture
  • configurable launch options
  • domain allowlists
  • rate limits
  • timeouts
  • audit logging

For agent workflows, I think the main question is not just can the agent browse?

The better question is: can it browse inside explicit limits?

A browser MCP server should make unsafe behavior harder by default.

Useful cases:

  • QA checks
  • scraping allowed pages
  • internal admin workflows
  • visual inspection
  • automation prototypes
  • agent-driven browser tasks

I am interested in feedback from people building MCP tools.

Which browser permissions should be default-off?

And what security controls should every browser automation MCP include?

Top comments (0)