MCP 服务器

xtapdown-mcp

An MCP server that provides LLM clients with direct access to XTapDown's Twitter creator toolkit, enabling tweet downloads, engagement calculations, content generation, and trend analysis without authentication or rate limits.

README

XTapDown MCP Server

An MCP (Model Context Protocol) server that gives any LLM client — Claude Desktop, Cursor, Cline, Continue, or your own agent — direct access to the XTapDown X (Twitter) creator toolkit.

Six tools, zero auth, zero rate limits for the data tools, free.

Tools (14)

Full coverage of every XTapDown web tool — 4 downloaders (video, GIF, image, full archive) consolidated under a single download_tweet since they share one X syndication endpoint.

Tool	Description
`download_tweet`	Download any X post — video, GIF, image, or article. Returns direct media URLs, author info, engagement stats. Covers /twitter-video-downloader, /twitter-gif-downloader, /twitter-image-downloader and /tweet-downloader.
`get_x_hashtags`	Curated X hashtags for a niche (tech, finance, marketing, politics, sports, business, ai, gaming, writing, fitness, design, general) + strategy tips.
`get_best_time_to_post_x`	Best posting windows on X by country (12 countries) with the reasoning behind each slot.
`generate_tweet_hook`	Battle-tested tweet hook formulas across 8 categories (Curiosity, Controversy, Authority, List, Story, Question, Numbers, Reframe).
`calculate_x_engagement_rate`	Compute engagement rate using the public follower-based formula, with tier-aware benchmark bands.
`calculate_x_ads_revenue`	Estimate monthly Premium creator ads-revenue-share payout from impressions, with eligibility check.
`get_x_trends`	Live trending topics on X by country (17 countries) — refreshed roughly hourly.
`count_tweet_characters`	X-weighted character count (CJK ×2, emoji ×2, URLs ×23 t.co) with thread-split warning.
`split_long_text_into_thread`	Split long text into ≤280-char numbered tweets respecting sentence/word boundaries + t.co URL math.
`build_x_search_url`	Build an X advanced-search URL from structured filters (from:, since:, min_faves:, lang:, filter:media, etc).
`generate_fancy_unicode_text`	Convert ASCII to fancy Unicode (bold, italic, monospace, script, double-struck, small-caps, bold-italic) for bios and tweets.
`get_tweet_screenshot_url`	Deep-link to the XTapDown screenshot tool with theme + background presets pre-filled (PNG rendering happens client-side in the browser).
`find_viral_tweets_for_niche`	Top creators in a niche plus 3 viral tweet templates with explanations of why each one works.
`get_x_search_operators_cheatsheet`	Full X advanced-search operator reference, grouped by category, updated for 2026.

Install

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "xtapdown": {
      "command": "npx",
      "args": ["-y", "xtapdown-mcp"]
    }
  }
}

Cursor / Cline / Continue

Add a stdio MCP server entry pointing at:

npx -y xtapdown-mcp

From source

git clone https://github.com/farukkolip/xtapdown-mcp
cd xtapdown-mcp
npm install
npm run build
node dist/index.js

Hosted (HTTP)

Set PORT=3000 (or any port) to start the server in HTTP / SSE mode for Smithery-style hosted deployments. Endpoint: POST /mcp and GET /mcp following the MCP Streamable HTTP transport spec.

Example interactions

"Download this tweet for me: https://x.com/.../status/..." → download_tweet returns direct MP4, thumbnail, author handle, like count.

"What's the best time to post on X if my audience is in Türkiye?" → get_best_time_to_post_x returns day-by-day windows in TRT.

"My 50k-follower account got 1,200 likes, 80 reposts, 150 replies. What's my engagement rate?" → calculate_x_engagement_rate returns 2.86% (Good — Mid tier).

"I've been getting 8M impressions a month. Would I qualify for ads revenue share?" → calculate_x_ads_revenue returns: projected 24M / 25M threshold = not yet eligible, ~$60/mo estimated payout if you cross.

Why MCP?

X's API is largely closed to creators. Most third-party tools require paid subscriptions or scrape with hidden rate limits. This server uses X's own public syndication endpoint (the same one embed widgets use) plus inline curated content data, so it works offline-free, no auth, no quota, no surprises.

Once added to your MCP client, the LLM can autonomously fetch tweet data and apply XTapDown's research data to whatever you're working on — content drafts, social audits, strategy threads, monetization math.

Data sources

Tweet data: cdn.syndication.twimg.com/tweet-result (public, auth-free)
Hashtags / best times / hooks / benchmarks: XTapDown editorial library, 2026 updated
Engagement math: public follower-based formula (likes + reposts + replies + bookmarks + quotes) / followers × 100
Ads revenue math: X Premium Creator Ads Revenue Sharing documented terms (25M imp/3mo + 500 verified followers + Premium)