Puppeteer MCP Server
by Model Context Protocol (reference)
Reference Puppeteer-backed MCP. Give an agent a real browser when an API does not exist.
MCP
Puppeteer MCP Server
Added 17 May 2026
Overview
The Puppeteer MCP server gives agents a real Chrome browser via Puppeteer: navigate, click, fill, screenshot, evaluate JavaScript. The right pick when the target surface has no API, and a complement (not a replacement) for Playwright MCP for teams that prefer Puppeteer's ergonomics.
Best for
Best for
Teams whose existing tooling is Puppeteer-based, or who need raw browser control
Use cases
- Drive a third-party UI an agent has no API for
- Scrape and parse a complex JavaScript-heavy page
- Capture screenshots for QA or audit trails
- Run scripted browser flows from an agent loop
Notes
Why it matters
Most real workflows still hit a surface with no API. The Puppeteer MCP server is one of two cleanest browser-as-tool answers in the reference set.
How teams use it in production
Use for one-off scrapes, third-party UIs without APIs, and visual audit flows. Always wrap in retries and human review for high-stakes runs.
What to watch
Browser-agent surfaces (Browserbase, Browser Use, Puppeteer MCP, Playwright MCP) are converging. Pick on ergonomic fit, not capability gap.
Pros
- Real browser, real DOM, no API gaps
- Reference quality with the protocol
- Familiar API for teams already on Puppeteer
- Pairs cleanly with Playwright MCP if both ecosystems matter
Cons
- Browser automation is inherently brittle on third-party sites
- Resource-heavy compared to API-first approaches
- Less first-class than Playwright in modern agent stacks
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Fetch MCP Server
Anthropic (reference implementation)
Reference MCP server for fetching web pages and converting them to markdown. Point an agent at any URL.
Playwright MCP
Microsoft
Browser control as an MCP server. Click, type, screenshot, scrape, all from inside any MCP-aware agent.