Is this an official Twitter API?
No, it uses the unofficial `twikit` library and is not endorsed by Twitter/X. It may break without notice and is intended for educational/experimental purposes only.

@dewkiks
基本情報
Twitter MCP Server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"twitter": {
"command": "python",
"args": [
"./path/to/server.py"
],
"env": {
"TWITTER_CT0": "your_ct0_here",
"TWITTER_AUTH_TOKEN": "your_auth_token_here"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Model Context Protocol (MCP) server that enables AI assistants to interact with Twitter using cookie-based authentication. It leverages the unofficial twikit library for Twitter integration and is intended for educational/experimental use.
Install via Smithery or manually clone the repository and install dependencies with pip install -r requirements.txt. Obtain the ct0 and auth_token cookies from your logged-in Twitter/X browser session, then configure Claude Desktop by adding environment variables TWITTER_CT0 and TWITTER_AUTH_TOKEN to the server entry in claude_desktop_config.json.
No, it uses the unofficial `twikit` library and is not endorsed by Twitter/X. It may break without notice and is intended for educational/experimental purposes only.
You need the `ct0` (CSRF token) and `auth_token` (authentication token) from your Twitter/X browser session, accessible via Developer Tools > Application/Storage > Cookies.
You can install automatically via Smithery using `npx -y @smithery/cli install @dewkiks/twitter-mcp-server --client claude`, or manually by cloning the repository and running `pip install -r requirements.txt`.
Available tools include `tweet`, `like_tweet`, `retweet`, `search_tweets`, `get_user_info`, `get_timeline`, `send_dm`, `get_dm_history`, `add_reaction_to_message`, `delete_dm`, `get_tweet_replies`, and `get_trends`.
Account restrictions are possible. The server uses an unofficial API that may break without notice. Use at your own risk.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns
コメント