Puppeteer
This Puppeteer-based MCP server, developed by Anthropic, enables browser automation and web interaction capabilities for AI models. It provides tools for navigating web pages, taking screenshots, clicking elements, filling forms, and executing JavaScript in a real browser environment. The server uses Puppeteer to control either a headless Chromium instance (in Docker) or a visible browser window (when run locally). It integrates with TensorFlow.js for text embedding generation. This implementation is particularly useful for web scraping, automated testing, and scenarios where AI models need to interact with web content in a realistic browser context.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/jwaldor/mcp-scrape-copilot
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Puppeteer 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.