Log inSubmit server
X Reader logo

X Reader

Reads web, social, video, podcast, and feed URLs into structured content with explicit evidence states for missing source layers.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install X Reader

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "x-reader": {
      "command": "uvx",
      "args": [
        "yt-dlp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command installed and started the server, which then stopped for configuration (such as an API key) that our sandbox does not have — expected for servers that connect to your account.

uvx yt-dlp

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked Today.

Overview

x-reader MCP server reads URLs from X, articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, RSS, and the open web. It selects source-specific readers, normalizes retrieved material, and reports whether the original source and relevant media were actually consumed. Evidence states distinguish PASS, PARTIAL, FAIL, and UNKNOWN instead of treating previews, captions, or metadata as complete source evidence. Reach for x-reader when an agent needs source-first research, media-aware reading, or machine-readable evidence about what was retrieved.

Use cases

  • Read a URL and produce structured source content
  • Check whether attached video or audio was actually consumed
  • Generate JSON evidence receipts for research workflows
  • Inspect RSS, podcast, and article sources
  • Verify source gaps before summarizing mixed-media posts

Key features

  • Source-specific readers for 10+ platforms
  • Evidence states: PASS, PARTIAL, FAIL, and UNKNOWN
  • JSON URL reading and evidence receipts
  • Subtitle and optional transcription workflows
  • Read-only doctor self-check
  • Local evidence web preview

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Supply-chain signal

8 high-severity advisories on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 0High 8Medium 3Low 11

Scanned 20h ago via OSV.dev · yt-dlp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars988Stargazers on the source repository.
Last commitTodayMost recent push to the default branch.
Install checkRunsOur sandbox started it; it then asked for an API key or config.

How X Reader works

What x-reader MCP server does

x-reader MCP server gives an AI agent a URL-oriented reading workflow for more than ten source types. It handles X/Twitter posts, web pages and articles, YouTube, Bilibili, WeChat, Xiaohongshu, Telegram, RSS, Xiaoyuzhou, Apple Podcasts, and other open-web URLs. Retrieved material is normalized into structured source content for research, summarization, and automation.

Its defining behavior is evidence tracking. A search result, post caption, video title, or description is treated as a limited layer rather than proof that the underlying source was read. The result can be marked PASS, PARTIAL, FAIL, or UNKNOWN depending on source access, media coverage, and verification.

How it works

The reader chooses a source-specific path. X/Twitter uses oEmbed, FxTwitter, article or Jina retrieval, and Playwright where applicable. Web pages use a pinned direct read that checks redirects and embedded audio or video before falling back to Jina Reader text. YouTube uses yt-dlp metadata and subtitles, with an optional Groq Whisper fallback. Other platforms use their respective APIs, browser workflows, feed parsing, Telethon, or episode-page extraction.

When a URL redirects to a recognized platform, x-reader passes it to that platform's reader. The Agent Skill can also inspect attached media with local tools. For example, X post text may be readable while an attached video remains PARTIAL until its relevant spoken or visual content is handled. Subtitle coverage can provide spoken-content evidence, but it does not establish that the video's images were analyzed.

The command-line path supports URL reading and JSON output through x-reader URL --json. The read-only x-reader doctor command performs a local self-check. A separate x-reader-web surface projects the same result into an evidence receipt for public X, YouTube, and generic web URLs.

Setup and configuration

The project requires Python 3.10 or newer. Its plugin starts the MCP server with uvx, so uv must be installed. The bundled Agent Skill can be installed with:

Terminal
npx skills add runesleo/x-reader --skill x-reader

The repository also supports plugin installation for Claude Code, Codex, and Cursor. Optional source workflows require additional local setup. Telegram reading needs Telegram credentials; Xiaohongshu may require a one-time local login; transcription can use the opt-in local ASR workflow or the Groq fallback when configured.

To run the local evidence web surface, install the project and start x-reader-web, for example:

Terminal
pip install -e .
x-reader-web --host 127.0.0.1 --port 8787

Tools and capabilities

  • Read public and source-specific URLs through an MCP-connected agent workflow.
  • Extract article and web-page text, X post content, RSS entries, podcast notes, subtitles, and platform metadata.
  • Handle audio or video completion paths where the required local tools, credentials, or transcription settings are available.
  • Return machine-readable JSON and evidence receipts.
  • Report PASS, PARTIAL, FAIL, or UNKNOWN states.
  • Run a read-only environment check with x-reader doctor.

Limitations and notes

Access and coverage vary by platform and can change over time. Login walls, deleted pages, paywalls, cookie walls, empty responses, and incomplete media can produce PARTIAL, FAIL, or UNKNOWN rather than a completed read. Public WeChat articles use browser fallback, while saved login sessions are not used. The hosted evidence-receipt beta accepts public X/Twitter, YouTube, and generic web URLs and uses an isolated temporary environment without saved browser sessions, Telegram credentials, Groq keys, Obsidian paths, or external X cookies.

Retrieved pages, posts, transcripts, subtitles, metadata, and comments should be treated as untrusted data rather than agent instructions. The evidence contract also distinguishes spoken-content coverage from visual analysis: reading subtitles does not mean the video images were examined.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about X Reader

x-reader is an MCP server that connects AI agents to X/Twitter, web pages, video platforms, podcasts, feeds, and other sources. Its main capabilities are URL reading, structured source extraction, JSON evidence receipts, and explicit PASS, PARTIAL, FAIL, or UNKNOWN results when media or source layers remain incomplete.

Install the bundled Agent Skill with `npx skills add runesleo/x-reader --skill x-reader`, then configure the MCP server through your agent. Plugin installation is also available for Claude Code, Codex, and Cursor, with `uv` required because the plugin starts the server using `uvx`.

Yes, x-reader supports Cursor through the repository's Cursor plugin configuration. The repository includes a `.cursor-plugin/plugin.json`; the Cursor Marketplace listing is not live, so installation uses the repository-based plugin path.

Yes, x-reader can retrieve YouTube metadata and subtitles, and it can use a configured Groq Whisper fallback for transcription. Attached media is tracked separately from post text, so a source may remain `PARTIAL` when relevant audio or video content was not consumed.

Optional sources may need additional setup: Telegram requires Telegram credentials, Xiaohongshu may require a one-time local login, and transcription can use configured Groq access or local ASR options. The hosted evidence beta does not inherit these credentials and accepts public X, YouTube, and generic web URLs.

Related MCP servers

All in Search & Data Extraction All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewX Reader AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/x-reader?style=directory)](https://allmcps.com/mcp/x-reader)
HTML Embed
<a href="https://allmcps.com/mcp/x-reader"><img src="https://allmcps.com/api/badge/x-reader?style=directory" alt="X Reader on AllMCPs" /></a>