Read Website Fast
This MCP server provides fast web content extraction and conversion to clean Markdown format, built by Just Every using TypeScript with Mozilla Readability for intelligent article detection and Turndown for HTML-to-Markdown conversion. It features disk-based caching, robots.txt compliance, concurrent crawling with configurable depth, and both CLI and MCP server modes for flexible integration. The implementation uses JSDOM for DOM parsing, supports relative URL conversion to absolute URLs, and includes smart content detection that applies Readability extraction only to clear article/blog pages while preserving full page content for other types of websites. Valuable for AI assistants that need to quickly extract and process web content for research, documentation, or content analysis workflows where clean Markdown output and fast performance are priorities.
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/just-every/mcp-read-website-fast
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Read Website Fast 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.