my-mcp-server
Provides tools for greetings, calculations, weather, geocoding, and image generation via Hugging Face, deployable to Vercel and integrable with Cursor.
README
my-mcp-server
Next.js + mcp-handler 기반 Streamable HTTP MCP 서버입니다. Vercel에 배포할 수 있습니다.
구조
app/
api/[transport]/route.ts # HTTP MCP 엔드포인트 (/api/mcp)
page.tsx
layout.tsx
lib/mcp/
server.ts # 도구·프롬프트·리소스 등록
helpers.ts
request-context.ts # x-hf-token 요청 컨텍스트
로컬 실행
npm install
npm run dev
MCP 엔드포인트: http://localhost:3000/api/mcp
MCP Inspector로 테스트
npx @modelcontextprotocol/inspector
- Transport: Streamable HTTP
- URL:
http://localhost:3000/api/mcp
Cursor 연결
로컬:
{
"mcpServers": {
"my-mcp-server": {
"url": "http://localhost:3000/api/mcp",
"headers": {
"x-hf-token": "hf_your_token_here"
}
}
}
}
Vercel 배포 후:
{
"mcpServers": {
"my-mcp-server": {
"url": "https://YOUR_PROJECT.vercel.app/api/mcp",
"headers": {
"x-hf-token": "hf_your_token_here"
}
}
}
}
HF 토큰 (x-hf-token)
generate-image 도구는 Hugging Face Inference API를 사용합니다. 토큰 우선순위:
- 요청 커스텀 헤더
x-hf-token(클라이언트별 입력) - 서버 환경변수
HF_TOKEN(선택적 폴백)
클라이언트에서 헤더로 넘기면 서버에 토큰을 고정 저장하지 않아도 됩니다.
Vercel 배포
npx vercel
또는 GitHub 연동 후 Vercel 대시보드에서 Import.
선택적으로 서버 공통 폴백 토큰을 쓰려면 Vercel 프로젝트에 HF_TOKEN을 설정하세요.
참고:
제공 기능
| 종류 | 이름 | 설명 |
|---|---|---|
| Tool | greet |
인사말 |
| Tool | calculator |
사칙연산 |
| Tool | get-time |
타임존 현재 시간 |
| Tool | geocode |
도시 → 좌표 |
| Tool | get-weather |
날씨/예보 |
| Tool | generate-image |
FLUX.1-schnell 이미지 생성 |
| Resource | info://server |
서버 정보 |
| Prompt | code-review |
코드 리뷰 프롬프트 |
스크립트
npm run dev— 로컬 개발 서버npm run build— 프로덕션 빌드npm start— 프로덕션 서버
라이선스
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.