HTML Page Preview
This MCP file preview server, developed by Sean Horvath, provides HTML file preview and analysis capabilities for AI assistants. Built with TypeScript and leveraging Puppeteer, it offers tools for capturing full-page screenshots and analyzing HTML structure. The server implements local file handling, screenshot management, and content analysis to enable advanced file previewing. Key features include customizable viewport sizes, headless browser automation, and detailed HTML element counting. By abstracting the complexities of rendering and parsing HTML files, it allows AI systems to easily visualize and understand web content. This implementation is particularly valuable for web testing, content analysis, and documentation tasks, facilitating use cases such as automated UI testing, web scraping, and generating visual aids for AI-assisted web development.
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/seanivore/mcp-file-preview
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve HTML Page Preview 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.