Glasses
This MCP server provides website screenshot capabilities using Puppeteer for headless Chrome automation, enabling AI assistants to capture visual snapshots of web pages with configurable device emulation and output formats. Built by Abderrahmane Gourragui with TypeScript and the Model Context Protocol SDK, it features device emulation for various screen sizes (iOS, Android, tablets, laptops with different DPI settings), support for both PNG and JPEG formats, full-page or viewport-only capture options, and robust error handling with comprehensive logging. The implementation uses Puppeteer's headless Chrome instance with sandbox-disabled arguments for compatibility, waits for network idle before capturing to ensure complete page loads, and automatically handles file path extensions based on the selected format, making it valuable for web development workflows, automated testing documentation, content auditing, and building AI assistants that need programmatic access to visual web page content without manual browser navigation.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/gourraguis/glasses-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Glasses 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.