Social APIS Hub
The unified API for social media data - built for developers and AI agents.
SocialAPIs MCP Server
🚀 Quick Start
Installation
npm install -g @socialapis/mcp
Configuration
Add to your Claude Desktop config:
macOS:
nano ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows:
notepad %APPDATA%\Claude\claude_desktop_config.json
🔧 Configuration
Method 1: Command Line Argument (Recommended for Claude Desktop)
{
"mcpServers": {
"socialapis": {
"command": "npx",
"args": ["-y", "@socialapis/mcp", "YOUR_API_KEY"]
}
}
}
Method 2: Environment Variable
# Set environment variable
export SOCIALAPIS_API_KEY=your_api_key_here
# Run without argument
npx @socialapis/mcp
Method 3: .env File (For Development)
# Copy example file
cp .env.example .env
# Edit with your values
nano .env
.env file:
SOCIALAPIS_API_KEY=your_api_key_here
MCP_PROXY_URL=https://mcp.socialapis.io
Environment Variables
| Variable | Description | Default |
|---|---|---|
SOCIALAPIS_API_KEY | Your SocialAPIs API key | None (required) |
MCP_PROXY_URL | MCP proxy server URL | https://mcp.socialapis.io |
PORT | HTTP server port | 3001 |
API_BASE_URL | Backend API URL | https://api.socialapis.io |
Get API Key
- Sign up at socialapis.io
- Go to Dashboard
- Copy your API key
- Replace
YOUR_API_KEYin config
Test It
Restart Claude Desktop and ask:
Get Nike's Facebook page details
📋 Features
- 🌐 Unified API - One interface for multiple platforms
- 🤖 AI-First - Built for Claude, Cursor, and AI agents
- 📊 Rich Data - Posts, comments, engagement metrics
- 🔍 Advanced Filtering - Time ranges, pagination
- 🎯 Simple Auth - No OAuth complexity
- ⚡ Fast - Global edge network
- 🔒 Secure - API keys stay local
🛠️ Available Tools
Facebook Pages
facebook_get_page_id- Extract page ID from URLfacebook_get_page_details- Get page info, followers, likesfacebook_get_page_posts- Fetch posts with time filteringfacebook_get_page_reels- Get reels/short videos
Facebook Groups
facebook_get_group_id- Extract group ID from URLfacebook_get_group_details- Get group metadatafacebook_get_group_posts- Fetch group posts
Facebook Posts
facebook_get_post_id- Extract post ID from URLfacebook_get_post_details- Get reactions, comments, sharesfacebook_get_post_attachments- Get media attachmentsfacebook_get_video_details- Get video metadatafacebook_get_post_comments- Fetch comments with pagination
More platforms coming soon: Instagram, TikTok, YouTube, Twitter
💡 Usage Examples
Brand Monitoring
Monitor Nike's Facebook page and alert me if engagement drops below average
Competitive Analysis
Compare engagement rates between Nike, Adidas, and Puma over the last month
Content Strategy
What types of posts get the most engagement on Coca-Cola's Facebook page?
Sentiment Analysis
Analyze comments on our recent posts and identify common themes
🏗️ Architecture
Claude Desktop
↓
@socialapis/mcp (local MCP client)
↓
https://mcp.socialapis.io (global proxy)
↓
https://api.socialapis.io (data API)
Why this architecture?
- ✅ Low latency (global edge network)
- ✅ High reliability (99.9% uptime)
- ✅ Auto rate limiting
- ✅ Smart caching
- ✅ Your API key stays local
🔧 Development
Local Setup
# Clone repository
git clone https://github.com/SocialAPIsHub/mcp-server.git
cd mcp-server
# Install dependencies
npm install
# Run MCP client
npm start YOUR_API_KEY
# Run HTTP proxy server
npm run serve
Project Structure
mcp-server/
├── src/
│ └── tools.js # Tool definitions
├── mcp-wrapper.js # MCP client (runs locally)
├── server.js # HTTP proxy server
├── package.json
├── Dockerfile
└── README.md
Testing
# Test MCP client locally
node mcp-wrapper.js YOUR_API_KEY
# Test HTTP proxy
curl http://localhost:3001/health
curl http://localhost:3001/tools
# Test specific tool
curl -X POST http://localhost:3001/proxy \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"facebook_get_page_details","arguments":{"link":"https://facebook.com/nike"}}'
📊 Pricing
| Plan | Requests/Month | Price |
|---|---|---|
| Free | 200 | $0 |
| Starter | 30,000 | $49 |
| Pro | 120,000 | $179 |
| Enterprise | Unlimited | Custom |
🤝 Contributing
We welcome contributions! Please see CONTRIBUTING.md for details.
Quick Contribution Guide
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📖 Documentation
💬 Support
- 📧 Email: [email protected]
- 💬 Discord: discord.gg/socialapis
- 🐛 Issues: GitHub Issues
- 📚 Docs: docs.socialapis.io
🗺️ Roadmap
- Facebook API support
- MCP server implementation
- HTTP proxy server
- npm package published
- Instagram support
- TikTok support
- YouTube support
- Twitter/X support
- Real-time webhooks
- Advanced analytics
- Python SDK
- LangChain integration
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Built with Model Context Protocol
- Powered by Anthropic Claude
- Inspired by the AI agent community
🌟 Star History
相关服务器
Bright Data
赞助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Feed
A server for fetching and parsing RSS, Atom, and JSON feeds.
Buienradar
Fetches precipitation data for a given latitude and longitude using Buienradar.
Simple MCP Tool Server
A simple MCP server that provides a tool for fetching website content using SSE transport.
Sports MCP Server
Live sports scores and stats from NBA, NFL, and NHL
TradingView Chart Image Scraper
Fetches TradingView chart images for a given ticker and interval.
GeekNews MCP Server
Fetches and caches daily articles from GeekNews using web scraping.
Scrapezy
Turn websites into datasets with Scrapezy
Sports Trading Card Agent
Real-time sports card pricing, market analysis, arbitrage detection, grading ROI, investment advice, and player stats (NBA/NFL/MLB). 9 tools for AI agents helping collectors and investors.
Puppeteer MCP Server
Automate browser interactions using Puppeteer, controlling new or existing Chrome instances.
https://prowldata.dev/mcp
Real-world intelligence for AI agents via x402 micropayments. Prediction markets, economics, weather, narrative, and geopolitics.
