ifrc-go-admin-mcp-server
Provides access to IFRC GO Admin API for disaster relief emergency fund (DREF) data, including operations, appeals, and emergencies.
README
IFRC GO Admin API MCP Server
A Model Context Protocol (MCP) server that provides access to the International Federation of Red Cross and Red Crescent Societies (IFRC) GO Admin API for disaster relief emergency fund (DREF) data.
Features
- DREF Operations: Access completed and ongoing disaster relief emergency fund operations
- Appeals: Query humanitarian funding appeals
- Emergencies: Get emergency event and disaster data
- Search & Filter: Search by country, disaster type, and other criteria
- Caching: Built-in response caching to reduce API load
- Pagination: Handle large datasets efficiently
Prerequisites
- Node.js 18.0.0 or higher
- npm or yarn package manager
- MCP-compatible client (Claude Desktop, etc.)
Installation
1. Install Dependencies
npm install
2. Build the Project
npm run build
3. Test the Server
npm start
Usage
Configure in Claude Desktop
Add to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"ifrc-go-admin": {
"command": "node",
"args": ["/path/to/your/ifrc-go-admin-mcp-server/dist/index.js"]
}
}
}
Available Tools
- get_completed_drefs: Retrieve completed DREF operations
- get_ongoing_drefs: Get currently active DREF operations
- get_appeals: Access humanitarian appeals for funding
- get_emergencies: Query emergency events and disasters
- search_drefs_by_country: Find DREF operations by country ISO code
- search_drefs_by_disaster_type: Search by disaster type (flood, earthquake, etc.)
- get_dref_statistics: Get summary statistics about DREF operations
Example Queries for AI Assistants
- "Show me recent earthquake-related DREF operations"
- "What are the ongoing emergency appeals in Bangladesh?"
- "Compare funding amounts for cyclone vs flood disasters this year"
- "List all completed DREF operations in West Africa"
Development
Scripts
npm run build- Compile TypeScript to JavaScriptnpm run dev- Watch mode for developmentnpm start- Start the production servernpm test- Test server startup
API Exploration
Before implementing, explore the API endpoints:
# Test basic connectivity
curl "https://goadmin.ifrc.org/api/v2/dref/?limit=1"
# Check completed DREFs
curl "https://goadmin.ifrc.org/api/v2/completed_dref/?limit=5"
# Search by country
curl "https://goadmin.ifrc.org/api/v2/dref/?country__iso=BD"
Adding New Endpoints
- Update Types: Add TypeScript interfaces for new data structures
- Extend API Client: Add methods to
IFRCAPIClientclass - Register Tools: Add tool definitions in
ListToolsRequestSchemahandler - Implement Handlers: Add case in
CallToolRequestSchemahandler
Pagination Best Practices
Following IFRC API documentation guidelines:
- Default limit is 50 records per page
- Maximum limit is 1000 records per page
- Stop pagination when returned records < limit
- Check for empty array [] to confirm no more data
- Use offset-based pagination with limit/offset parameters
Rate Limiting Considerations
The server includes basic caching (5-minute timeout) to be respectful of IFRC's infrastructure. For production use:
- Implement exponential backoff for retries
- Add request rate limiting
- Monitor API usage and respect any documented limits
- Consider using webhooks for real-time updates if available
Error Handling
The server includes comprehensive error handling:
- HTTP errors from the API
- Invalid parameters
- Network timeouts
- Cache management
Authentication
Currently, the IFRC GO Admin API appears to be publicly accessible. If authentication is required:
- Add API key management to the
IFRCAPIClientclass - Include authentication headers in requests
- Handle authentication errors appropriately
Data Schema Examples
DREF Operation
{
"id": 12345,
"title": "Bangladesh: Cyclone Mocha",
"country": "Bangladesh",
"disaster_type": "Cyclone",
"amount_requested": 500000,
"amount_funded": 500000,
"disaster_start_date": "2023-05-14",
"status": "completed"
}
Emergency Event
{
"id": 67890,
"name": "Morocco Earthquake September 2023",
"countries": ["Morocco"],
"disaster_type": "Earthquake",
"num_affected": 300000,
"disaster_start_date": "2023-09-08"
}
Project Structure
ifrc-go-admin-mcp-server/
├── src/
│ └── index.ts # Main MCP server implementation
├── dist/ # Compiled JavaScript output
├── package.json # Project configuration
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Submit a pull request
Humanitarian Use Guidelines
This server provides access to sensitive humanitarian data. Please:
- Use responsibly and respect the humanitarian context
- Don't overwhelm the IFRC API with excessive requests
- Consider data privacy when analyzing beneficiary information
- Contribute improvements back to the humanitarian community
Support
For issues related to:
- MCP Server: Open an issue in this repository
- IFRC GO API: Contact IFRC technical support
- Data Questions: Refer to IFRC GO documentation
License
MIT License - See LICENSE file for details.
Acknowledgments
- International Federation of Red Cross and Red Crescent Societies
- Model Context Protocol development team
- Open source humanitarian technology community
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。