thread-storm

thread-storm

MCP server for publishing threads to Threads and Twitter/X simultaneously from Claude Code. Journal your thoughts, convert them to viral threads, and post everywhere at once.

Category
访问服务器

README

Thread Storm

MCP server for publishing threads to Threads and Twitter/X simultaneously from Claude Code. Journal your thoughts, convert them to viral threads, and post everywhere at once.

Features

13 tools available via MCP:

Threads (9 tools)

Tool Description
threads_get_profile Fetch Threads profile info
threads_get_posts List recent posts with pagination
threads_get_post_details Get full details for a specific post
threads_get_post_insights Engagement metrics (views, likes, replies, reposts, quotes, shares)
threads_get_replies Direct replies to a specific post
threads_search Keyword search across Threads
threads_get_account_insights Account-level metrics
threads_publish_text Publish a text post (optional reply)
threads_publish_thread Publish a multi-post thread

Twitter/X (3 tools)

Tool Description
twitter_get_profile Fetch Twitter profile info
twitter_publish_text Post a tweet (optional reply)
twitter_publish_thread Post a tweet thread

Cross-Platform (1 tool)

Tool Description
storm_publish_thread Publish to BOTH Threads and Twitter simultaneously

Prerequisites

  • Python 3.12+
  • uv
  • A Meta developer app with Threads API access
  • A Twitter/X developer app with Read+Write permissions

Quick Start

  1. Clone the repo:

    git clone https://github.com/asadhuddleduck/thread-storm.git
    cd thread-storm
    
  2. Install dependencies:

    uv sync
    
  3. Add to your .mcp.json:

    {
      "mcpServers": {
        "thread-storm": {
          "command": "uv",
          "args": ["run", "--python", "3.12", "--directory", "/path/to/thread-storm", "thread-storm"],
          "env": {
            "THREADS_ACCESS_TOKEN": "your-threads-token",
            "THREADS_APP_SECRET": "your-threads-app-secret",
            "TWITTER_API_KEY": "your-twitter-api-key",
            "TWITTER_API_SECRET": "your-twitter-api-secret",
            "TWITTER_ACCESS_TOKEN": "your-twitter-access-token",
            "TWITTER_ACCESS_TOKEN_SECRET": "your-twitter-access-token-secret"
          }
        }
      }
    }
    
  4. Restart Claude Code. All 13 tools will be available.

Environment Variables

Variable Platform Description
THREADS_ACCESS_TOKEN Threads Long-lived token from Meta's User Token Generator
THREADS_APP_SECRET Threads App secret from Meta developer app
TWITTER_API_KEY Twitter OAuth 1.0a consumer API key
TWITTER_API_SECRET Twitter OAuth 1.0a consumer API secret
TWITTER_ACCESS_TOKEN Twitter OAuth 1.0a user access token
TWITTER_ACCESS_TOKEN_SECRET Twitter OAuth 1.0a user access token secret

Architecture

src/thread_storm/
  threads_client.py   — Threads HTTP client (GET via urllib, POST via curl)
  twitter_client.py   — Twitter client via tweepy (OAuth 1.0a)
  server.py           — FastMCP server with 13 tool definitions

Threads Publishing Flow

  1. Create media container (POST)
  2. Poll container status until FINISHED (2s intervals)
  3. Publish container (POST)
  4. Wait 10s propagation delay before next reply

Twitter Publishing Flow

  1. Post tweet (POST /2/tweets)
  2. Post next tweet with in_reply_to_tweet_id
  3. No polling or delays needed

storm_publish_thread

Runs both platforms in parallel using ThreadPoolExecutor. Twitter finishes in seconds while Threads takes 1-2 minutes for a 9-post thread.

Token Management (Threads)

Threads tokens expire after 60 days. Auto-refresh kicks in at day 30:

  1. Token saved to ~/.threads-mcp/token.json on first use
  2. After day 30, exchanged for a fresh 60-day token
  3. New token saved to both token.json and .mcp.json

Twitter OAuth 1.0a tokens do not expire.

Rate Limits

  • Threads publishing: 250 posts per 24 hours
  • Threads search: 500 queries per 7 days
  • Twitter publishing: 500 tweets per month (Free tier)

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选