Puppeteer Vision Web Scraper
Puppeteer Vision MCP Server provides a tool for scraping webpages and converting them to markdown format using Puppeteer, Mozilla's Readability, and Turndown. Developed by Denis Jannot, it features AI-driven interaction capabilities that automatically handle cookie consent banners, CAPTCHAs, paywalls, and other interactive elements blocking content. The server uses OpenAI's vision models to analyze screenshots of web pages and determine appropriate interactions, with special handling for code blocks, tables, and other structured content. Available as an NPX package with configurable headless mode, it supports both stdio and SSE transport methods, making it particularly valuable for AI assistants that need to extract and process web content without being blocked by interactive elements.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/djannot/puppeteer-vision-mcp
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Puppeteer Vision Web Scraper from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.