Claude 4.7과 함께하는 3시간: 기능 연구 웹앱 및 원격 MCP – Oneshotted
hackernews
|
|
📰 뉴스
#claude
#review
원문 출처: hackernews · Genesis Park에서 요약 및 분석
요약
CS 학생이 모든 강의 자료를 Claude Code에 입력해 단 3시간 만에 학습 대시보드와 MCP 서버를 구축한 성공 사례입니다. React, FastAPI, Supabase를 활용해 Vercel에 배포된 이 시스템은 강의, 과제, 시험을 관리하며 기기 간 동기화를 지원합니다. 특히 40개의 도구를 제공하는 MCP 서버는 Claude.ai, 데스크톱, iOS 앱 등 다양한 환경에서 강의 데이터에 접근할 수 있게 해주며, PDF 시각화 등 고급 기능도 포함되었습니다.
본문
Writeup + demo for a 3-hour build with Claude Code. The actual project is closed source (personal study dashboard with all my course data baked in) — this repo just exists to host the demo and the story. i'm a CS student and i wanted to organize my course stuff for the start of the semester. i went on moodle, downloaded all organizational PDFs of each course, all lectures, copied the course descriptions etc and i dumped it all into one folder on my laptop and told Claude Code to organize each one and write comprehensive .md files for each course (what is it about, when is the exam, what should be done across the semester, deadlines, etc) and then after it was done, i told it to build me a system around it. what i ended up with: - a fully functional study dashboard on Vercel (React + FastAPI + Supabase) tracking my four courses — lectures, topics, deliverables, exams. fully responsive on mobile, looks decent. - an MCP server with 40 tools. anything i can do in the UI the AI can do too — create a topic, mark something studied, upload a file, render a PDF as images, whatever. - plugged that MCP into Claude.ai as a custom connector. full OAuth 2.1 and everything. - which means those 40 tools are now available in Claude Code on my laptop, the Claude website, AND the Claude iOS app on my phone. i can just open Claude anywhere and it has access to all my course stuff. - two-way sync between my laptop's Semester 4/ folder and the bucket. push/pull/watch commands. bucket is the source of truth. i also made a custom Claude project (in claude.ai) with a system prompt i wrote, so every chat i start in that project already knows my workflow — which courses, how i transcribe lectures, when to mark something as studied vs covered etc. the part that actually made me post: the MCP that i made has a tool that takes a PDF path and returns the pages as images. i searched some Claude docs and they don't tell you whether it feeds those retrieved images to the model as vision input or just displays them in the UI as attachments when it pulls them through an MCP server. so i tested by asking Claude to describe stuff you can only get by actually looking at the slide and it worked. stuff broke along the way — Vercel's Python runtime doesn't fire ASGI lifespan, FastMCP has a DNS rebinding protection default that's localhost-only, Supabase Storage doesn't like German umlauts in filenames, iOS Safari won't scroll PDFs inside iframes. Claude hit every one of those, figured it out, fixed it. i never had to say "no do it differently" a SINGLE TIME. this is the first time i've experienced this with Claude Code tbh. 3 hours. from dumping a folder to a system i actually use daily from every device i own. - Frontend: Vite + React 19 + TypeScript + Tailwind - Backend: Python 3.12 + FastAPI - DB + Storage: Supabase Postgres + Storage bucket - MCP server: Python mcp SDK — stdio for Claude Code, streamable HTTP mounted at/mcp for Claude.ai - Auth: password-based dashboard session + OAuth 2.1 authorization server for the remote MCP (Dynamic Client Registration, PKCE-S256) - Hosting: Vercel (frontend + FastAPI as a Python function) The repo has my course data, lecture transcriptions, and personal notes all wired in. Cleaning it up to publish would take longer than the build itself did.
Genesis Park 편집팀이 AI를 활용하여 작성한 분석입니다. 원문은 출처 링크를 통해 확인할 수 있습니다.
공유