Puppeteer (local)
BetaBrowser automation and scraping with Puppeteer, run as a container.
- Automation
- Local
- Runs
- On the developer's Mac
- Launched with
- Docker
- Platform
- macOS
- Publisher
- Docker
How it works
Every agent request passes through Ferentin policy before it reaches Puppeteer (local).
It runs on the developer's Mac and talks to the AI client over stdio, so no network gateway sees it. Developers launch it with docker run -i --rm mcp/puppeteer.
Ferentin's endpoint agent finds Puppeteer (local) in the MCP configuration of AI clients on managed Macs. An administrator adds it once from the local MCP catalog for every managed Mac that launches it this way. Each of its tools starts unvetted until it is approved. Ferentin records every tool call.
- AI agentAsks for something
- Ferentin policies
- Puppeteer (local) MCP serverRuns on the developer's Mac
- Governed resultChecked, logged, returned
About Puppeteer (local)
Browser automation and scraping with Puppeteer, run as a container.
Frequently asked about Puppeteer (local)
- How do I connect Puppeteer (local) to Ferentin?
- Enroll your Macs with the Ferentin endpoint agent, then add Puppeteer (local) from the local MCP catalog in the Ferentin admin console. Every managed Mac that launches it the way the catalog names it is covered, and each of its tools starts unvetted until you approve it.
- Is the Puppeteer (local) integration generally available?
- The Puppeteer (local) integration is currently beta on Ferentin.
Related integrations
3
Brave Search (local)
Searches the web, images, news and video through the Brave Search API. Every query goes to Brave.
Elasticsearch (local)
Queries Elasticsearch indices in natural language, so whatever the indices hold becomes readable by the agent.
Redis (local)
Read and write access to a Redis database, run as a container.