SkyFi MCP Server
Enables AI agents to interact with SkyFi's geospatial data services for ordering satellite imagery, searching data catalogs, checking pricing and feasibility, and monitoring areas of interest.
README
SkyFi MCP Server
SkyFi Model Context Protocol (MCP) server for AI agent integration with geospatial data services.
Overview
SkyFi MCP enables AI agents to seamlessly interact with SkyFi's geospatial data services through a comprehensive RESTful API with Server-Sent Events (SSE) support. The server provides:
- Order Management: Create, track, and manage geospatial data orders
- Data Search: Iterative search and exploration of geospatial data catalogs
- Pricing & Feasibility: Check order feasibility and get pricing estimates
- Monitoring: Set up Area of Interest (AOI) monitoring with webhook notifications
- Framework Integration: Native support for ADK, LangChain, and AI SDK
Quick Start
Prerequisites
- Node.js >= 18.0.0
- Docker and Docker Compose
- PostgreSQL 15+ (or use Docker Compose)
- Redis 7+ (or use Docker Compose)
Installation
- Clone the repository:
git clone <repository-url>
cd skyfi-mcp
- Install dependencies:
npm install
- Copy environment file:
cp .env.example .env
-
Update
.envwith your configuration:- Set
SKYFI_API_KEYwith your SkyFi API key - Configure database and Redis URLs
- Set security keys (JWT_SECRET, API_KEY_ENCRYPTION_KEY)
- Set
-
Start services with Docker Compose:
docker-compose up -d
- Setup database (if using Docker Compose, database is created automatically):
# Option 1: Use the setup script
npm run db:setup
# Option 2: Manual setup
# First, ensure PostgreSQL is running, then:
psql -h localhost -U postgres -c "CREATE DATABASE skyfi_mcp"
psql -h localhost -U postgres -d skyfi_mcp -f scripts/init-db.sql
- Start the development server:
npm run dev
The server will be available at http://localhost:3000
Note: The server will start even if the database connection fails initially. You can set up the database later and the server will connect when it's available.
Development
Scripts
npm run dev- Start development server with hot reloadnpm run build- Build TypeScript to JavaScriptnpm start- Start production servernpm test- Run testsnpm run test:watch- Run tests in watch modenpm run test:coverage- Generate test coverage reportnpm run lint- Run ESLintnpm run lint:fix- Fix ESLint errorsnpm run format- Format code with Prettiernpm run type-check- Type check without building
Project Structure
skyfi-mcp/
├── src/
│ ├── server/ # Server setup and routes
│ ├── services/ # Business logic services
│ ├── repositories/ # Data access layer
│ ├── models/ # Data models and types
│ ├── auth/ # Authentication and credentials
│ ├── middleware/ # Express middleware
│ ├── utils/ # Utility functions
│ ├── config/ # Configuration
│ └── sse/ # Server-Sent Events
├── docs/ # Documentation
├── tests/ # Test files
├── scripts/ # Utility scripts
└── docker-compose.yml # Docker Compose configuration
API Documentation
API documentation is available at /docs/api when the server is running.
Base URL
- Development:
http://localhost:3000/v1 - Production:
https://api.skyfi-mcp.com/v1
Authentication
All API requests require an API key in the Authorization header:
Authorization: Bearer YOUR_API_KEY
Example Request
curl -X GET http://localhost:3000/v1/health \
-H "Authorization: Bearer YOUR_API_KEY"
Testing
Run the test suite:
npm test
Run tests with coverage:
npm run test:coverage
Docker
Build Image
docker build -t skyfi-mcp .
Run Container
docker run -p 3000:3000 \
-e SKYFI_API_KEY=your_key \
-e DATABASE_URL=postgresql://... \
skyfi-mcp
Docker Compose
Start all services:
docker-compose up -d
Stop all services:
docker-compose down
View logs:
docker-compose logs -f mcp-server
Environment Variables
See .env.example for all available environment variables.
Key variables:
SKYFI_API_KEY- Your SkyFi API key (required)DATABASE_URL- PostgreSQL connection stringREDIS_URL- Redis connection stringJWT_SECRET- Secret for JWT tokensAPI_KEY_ENCRYPTION_KEY- Key for encrypting API keys
Framework Integration
ADK
See docs/integration/adk.md for ADK integration guide.
LangChain
See docs/integration/langchain.md for LangChain integration guide.
AI SDK
See docs/integration/ai-sdk.md for AI SDK integration guide.
Contributing
- 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
License
MIT License - see LICENSE file for details
Support
For support, please open an issue in the repository or contact support@skyfi.com
Status
🚧 In Development - This project is currently in active development. See the PRD and Architecture Documentation for more details.
Version: 1.0.0
Last Updated: January 2025
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。