Readability (Fetch & Parse)
This Python-based MCP server, developed by JMH, provides a robust solution for extracting and transforming webpage content into clean, LLM-optimized Markdown. Built on FastMCP and integrating libraries like readability-lxml and html2text, it offers a single powerful tool for fetching, parsing, and converting web content. The implementation stands out by removing non-essential elements like ads and navigation, while preserving key metadata such as title, excerpt, and author. It's particularly useful for developers and researchers who need to process web content for AI analysis, content aggregation, or data extraction tasks, offering a more refined and consistent output compared to simple web scraping methods.
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
- ai-ml
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Readability (Fetch & Parse) 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.