# Readability (Fetch & Parse)

> Use this tool when you need to extract and transform webpage content into clean Markdown for AI analysis or content aggregation. It fetches and parses web pages, removing non-essential elements and preserving key metadata, providing a refined output for tasks like data extraction and LLM optimization. Ideal for developers and researchers, it offers a robust solution for processing web content, accepting URLs as input and producing LLM-optimized Markdown as output.

Canonical page: https://skillsregistry.net/skills/jmh-readability-parser  
JSON: https://api.skillsregistry.net/v1/skills/jmh-readability-parser

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/jmh-readability-parser)
- **Repository:** <https://github.com/jmh108/mcp-server-readability-python>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jmh-readability-parser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jmh-readability-parser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jmh-readability-parser/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt