x-reader

MCP.Pizza Chef: runesleo

This tool turns links from YouTube, X (Twitter), WeChat, Telegram, podcasts, and ordinary web pages into clean, readable text that your AI assistant can read and work with. Point it at a video and it pulls a full transcript; point it at a tweet or article and it pulls the text. It works with Claude Desktop, and setup involves installing a small Python program, plus a free key from Groq if you want video transcripts.

Notes
Web/Research

Use This MCP server To

Get a full transcript of a YouTube video or podcast Pull the readable text out of a tweet or X post Turn a long article or blog post into clean, readable text Read posts from WeChat, Xiaohongshu, or Telegram in one place Fetch several links at once and get them all back together Keep a running list of everything I've asked it to read Follow updates from an RSS feed without opening a browser

README

x-reader

Python 3.10+ License: MIT

Universal content reader — fetch, transcribe, and digest content from any platform.

Give it a URL (article, video, podcast, tweet), get back structured content. Works as CLI, Python library, MCP server, or Claude Code skills.

简体中文: README.zh.md / README.zh-CN.md

What It Does

Any URL → Platform Detection → Fetch Content → Unified Output
              ↓                      ↓
         auto-detect           text: Jina Reader
         7+ platforms          video: yt-dlp subtitles
                               audio: Whisper transcription
                               API: Bilibili / RSS / Telegram

The Python layer handles text fetching and YouTube subtitle extraction. The Claude Code skills (optional) add full Whisper transcription for video/podcast and AI-powered content analysis.

Three Layers

x-reader is composable. Use the layers you need:

Layer What Format Install
Python CLI/Library Basic content fetching + unified schema See Install Required
Claude Code Skills Video transcription + AI analysis Copy skills/ to your Claude Code skills directory Optional
MCP Server Expose reading as MCP tools python mcp_server.py Optional

Layer 1: Python CLI

# Fetch any URL
x-reader https://mp.weixin.qq.com/s/abc123

# Fetch a tweet
x-reader https://x.com/elonmusk/status/123456

# Fetch multiple URLs
x-reader https://url1.com https://url2.com

# Login to a platform (one-time, for browser fallback)
x-reader login xhs

# View inbox
x-reader list

x-reader FAQ

Can I use this to get a transcript of a YouTube video?
Yes — give it the video's link and it pulls the captions automatically. If the video has no captions, it can transcribe the audio instead, though that step needs a free account with Groq, the company that provides the transcription service.
Can I use this to read a tweet without opening X (Twitter)?
Yes — hand it the post's link and it returns the text, so your AI assistant (Claude, ChatGPT, or Gemini) can read, summarize, or act on it.
Which AI apps does this work with?
It is built and documented for Claude Desktop, and it connects the same way many AI apps connect to outside tools, so it should also work with other compatible apps.
Do I need an account or a key to use it?
Reading ordinary web pages, articles, and tweets needs nothing extra. Transcribing video or podcast audio that has no captions needs a free Groq account, and reading Telegram channels needs a free Telegram developer account.
How hard is this to set up?
This one is best suited to someone comfortable installing developer tools. It is a small program you install and run yourself from a command line rather than something you click to add.
Can I give it several links at once?
Yes — hand it a list of links and it fetches all of them and hands back the text for each one.
Will it work on posts that need me to be logged in?
For a couple of platforms, X and Xiaohongshu, it can use a saved login to reach content that needs sign-in, but this is optional and switched off by default.
Does it keep track of what I've already read?
Yes — it keeps a running list of everything you've fetched, so you can look back at earlier links without pulling them again.