Repolode
Submit
runesleo

runesleo/x-reader

Universal content reader MCP server that gives AI agents structured, evidence-graded text from X, YouTube, podcasts, WeChat, and other URLs.

View on GitHubWebsite
Stars
988
Forks
97
Open issues
3
Last commit
4 days ago

What is it?

x-reader turns a URL into normalized source content that AI agents can use for research, summarization, and automation. It covers X/Twitter, web articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, and RSS, and it can be used as a CLI, a Python library, an MCP server, or an Agent Skill.

Each read is labeled with an evidence state: PASS, PARTIAL, FAIL, or UNKNOWN. If attached video or audio is not consumed, or a podcast only yields show notes, the result stays PARTIAL rather than claiming full coverage. Fetched content is treated as untrusted data, and URLs targeting private or local addresses are blocked before network fetches.

The project includes a small web preview for public X, YouTube, and generic web URLs, and a `doctor` command that reports which read paths are ready. Some capabilities, such as Telegram, Groq Whisper transcription, and logged-in browser sessions, need credentials or local setup.

Key features

  • 01Reads X/Twitter, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, RSS, and web pages.
  • 02Labels every read with PASS, PARTIAL, FAIL, or UNKNOWN evidence states.
  • 03Exposes an MCP server with read_url, read_batch, list_inbox, and detect_platform tools.
  • 04Provides a CLI with JSON output for agents, plus a Python library interface.
  • 05Ships an Agent Skill that can be installed with npx skills.
  • 06Blocks private and local URL targets before fetching.

Use cases

  • Giving an AI assistant a link and having it summarize the original post, video, or article.
  • Checking whether a summary covers the attached video or podcast audio, not just the post text.
  • Adding multi-platform content reading to a Claude Code, Cursor, or Codex workflow through MCP.
  • Collecting structured text from social and video sources for research pipelines.

Quick start

  1. 1

    Install the CLI from GitHub

    pip install "x-reader @ git+https://github.com/runesleo/x-reader.git"
  2. 2

    Read a URL

    x-reader https://x.com/elonmusk/status/123456
  3. 3

    Check what is ready and what is missing

    x-reader doctor

Things to know

  • Browser fallback needs an extra install and a one-time login for some platforms like Xiaohongshu.
  • Telegram reading requires your own Telegram credentials.
  • Full podcast and YouTube audio transcription needs optional tools or API keys such as Groq.

In collections

Open-source AI agent frameworks & appsMCP servers

Topics

#mcp#ai-agents#content-extraction#web-scraping#youtube#twitter#python#mcp-server

FAQ

What is x-reader?
Universal content reader MCP server that gives AI agents structured, evidence-graded text from X, YouTube, podcasts, WeChat, and other URLs. x-reader turns a URL into normalized source content that AI agents can use for research, summarization, and automation. It covers X/Twitter, web articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, and RSS, and it can be used as a CLI, a Python library, an MCP server, or an Agent Skill.
Is x-reader free to use? What license does it have?
x-reader is open source under the MIT license. Check the license terms before using it in commercial products.
Is x-reader still maintained?
Actively maintained. The last commit to x-reader was on Nov 3, 2026.
What can I use x-reader for?
Giving an AI assistant a link and having it summarize the original post, video, or article. Checking whether a summary covers the attached video or podcast audio, not just the post text. Adding multi-platform content reading to a Claude Code, Cursor, or Codex workflow through MCP. Collecting structured text from social and video sources for research pipelines.
How do I install x-reader?
Install the CLI from GitHub: pip install "x-reader @ git+https://github.com/runesleo/x-reader.git" Read a URL: x-reader https://x.com/elonmusk/status/123456 Check what is ready and what is missing: x-reader doctor
Where can I get x-reader?
The source code and installation instructions are on GitHub: https://github.com/runesleo/x-reader

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects