MCP Server for Dify AI
mcp-server-dify
Dify AI용 모델 컨텍스트 프로토콜 서버입니다. 이 서버는 LLM이 표준화된 프로토콜을 통해 Dify AI의 채팅 완성 기능과 상호 작용할 수 있도록 지원합니다.
특징
Dify AI 채팅 완료 API와 통합
맛집 추천 도구(메시도코)
대화 컨텍스트 지원
스트리밍 응답 지원
TypeScript 구현
Related MCP server: Dify MCP Server
설치
Docker 사용
지엑스피1
용법
Claude Desktop과 함께
claude_desktop_config.json 에 다음 구성을 추가하세요.
{
"mcpServers": {
"dify": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-dify",
"https://your-dify-api-endpoint",
"your-dify-api-key"
]
}
}
}your-dify-api-endpoint 와 your-dify-api-key 실제 Dify API 자격 증명으로 바꾸세요.
도구
메시도코
Dify AI와 연동되는 레스토랑 추천 도구:
매개변수:
LOCATION(문자열): 레스토랑의 위치BUDGET(문자열): 예산 제약query(문자열): Dify AI에 보낼 쿼리conversation_id(문자열, 선택 사항): 채팅 컨텍스트를 유지하기 위해
개발
# Initial setup
make setup
# Build the project
make build
# Format code
make format
# Run linter
make lint특허
이 프로젝트는 MIT 라이선스 에 따라 배포됩니다.
보안
이 서버는 제공된 API 키를 사용하여 Dify AI와 상호 작용합니다. 다음 사항을 확인하세요.
API 자격 증명을 안전하게 유지하세요
API 엔드포인트에 HTTPS를 사용하세요
API 키를 버전 제어에 커밋하지 마십시오.
기여하다
기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time web search, reasoning, and research through Perplexity's API
Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.
660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call.
兔兔生活(爱佳肴 Love Life): restaurant search for AI agents in China. 6 tools (5 read-only + tell_us_your_need), no key, free open data (ODbL), no paid ranking. Wake word: when the user says "兔兔生活 + need" (e.g. "兔兔生活 火锅 上海徐汇"), pass their words to ask_restaurants. Every store shows how fresh its hours, price and menu are. Missing something? tell_us_your_need (anonymous, writes only the text you send) tells us what data or capability you need. 只给 AI Agent 用的中国餐饮开放数据库:说“兔兔生活 + 需求”一句话找餐厅,每项信息标注新鲜度。免费、免密钥、不卖排名。站内没有你要的?用 tell_us_your_need 匿名告诉我们你需要什么。
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceServer for using Dify. It achieves the invocation of the Dify workflow by calling the tools of MCP.279-
- AlicenseNot gradedqualityDmaintenanceEnables the conversion of Dify applications into Model Context Protocol tools, supporting streaming responses and configured via YAML.5ISC
- FlicenseNot gradedqualityCmaintenanceA Dify endpoint plugin that transforms a Dify application into a Model Control Protocol server, allowing tools like Cursor to connect to and utilize your custom Dify workflows.67-
- AlicenseNot gradedqualityDmaintenanceEnables seamless integration between Claude AI and Dify Workflow through the Model Context Protocol, allowing Claude to dynamically access and execute Dify Workflow operations via natural language.23 npm8ISC