Sociona MCP Server
Enables AI assistants to publish, schedule, and manage social media posts across X (Twitter), Instagram, and Threads through the Sociona API. Supports immediate posting, scheduling, analytics, and account management with natural language commands.
README
Sociona MCP Server
An MCP (Model Context Protocol) server that provides AI assistants and MCP-compatible tools with access to the Sociona social media API.
🚀 Features
- Publish Posts: Immediately publish content to social media platforms
- Schedule Posts: Schedule posts for future publication
- Cancel Scheduled Posts: Cancel posts before they publish
- List Accounts: View connected social media accounts
- Post History: Retrieve recent post history with filtering
- Analytics: Get statistics about your posts
- Multi-Platform Support: X (Twitter), Instagram, and Threads
📦 Installation
Quick Install
npm install -g sociona-mcp-server
Alternative Installation
# Using the installation script
curl -sSL https://raw.githubusercontent.com/fav-devs/sociona-mcp-server/main/install.sh | bash
⚙️ Configuration
1. Get Your API Key
- Sign up at Sociona Developer Portal
- Create a new application
- Generate an API key with required scopes:
posts:write- for publishing postsposts:read- for reading postsschedule:write- for scheduling postsschedule:read- for reading scheduled posts
2. Configure Your MCP Client
For Claude Desktop
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"sociona": {
"command": "sociona-mcp",
"args": [],
"env": {
"SOCIONA_API_KEY": "sk_live_your_api_key_here",
"SOCIONA_API_BASE": "https://api.sociona.app/api/v1"
}
}
}
}
For Other MCP Clients
Configure your MCP client to use the sociona-mcp command with the required environment variables.
3. Restart Your MCP Client
Restart your MCP client to load the new MCP server configuration.
💬 Usage
Once configured, you can use natural language commands with your MCP client:
"Post to Twitter: Just launched our new feature! 🚀 #TechNews"
"Schedule a post for Instagram tomorrow at 10 AM about our weekly roundup"
"Show me my connected social accounts"
"Get my last 10 posts from X"
"Cancel the scheduled post with ID sched-123"
"What's my posting statistics?"
🛠️ Available Tools
The Sociona MCP Server exposes the following tools:
publish_post: Publish a social media post immediatelyschedule_post: Schedule a social media post for future publicationget_accounts: List all connected social media accountsget_posts: Retrieve recent post historyget_scheduled_posts: View upcoming scheduled postscancel_scheduled_post: Cancel a scheduled post before it publishesget_post_stats: Get statistics about your posts
🔧 Development
Prerequisites
- Node.js 18 or higher
- npm or pnpm
Setup
# Clone the repository
git clone https://github.com/fav-devs/sociona-mcp-server.git
cd sociona-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Run in development mode
npm run dev
Scripts
npm run build- Build the TypeScript codenpm run dev- Run in development modenpm start- Start the MCP servernpm test- Run tests
📚 Documentation
- Developer Installation Guide - Detailed setup instructions
- Local Setup Guide - For local development
- Architecture Overview - Technical architecture details
- Railway Deployment - Cloud deployment guide
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🔗 Links
🆘 Support
If you encounter any issues or have questions:
- Check the Issues page
- Create a new issue if your problem isn't already reported
- Join our community discussions
Made with ❤️ by the Sociona team
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。