mixi-mcp
Hosts the MCP server and gallery page, with Cloudflare KV for storing interview results, deployed automatically via GitHub Actions.
Serves student-branded HTML pages that include a gallery link, allowing users to access the MIXI gallery from their custom page.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mixi-mcpStart a MIXI spatial preference interview"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MIXI MCP Server
MIXI 조명 브랜드의 공간 취향 인터뷰 MCP 서버입니다.
학생 가이드
1. Claude.ai 커넥터 연결
Claude.ai → Settings → Integrations → Add custom integration
URL: https://mixi-mcp.typica-918.workers.dev/mcp
연결 후 Claude와 대화를 시작하면 MIXI 인터뷰를 진행할 수 있습니다.
2. 이 repo fork
본인의 GitHub 계정으로 이 repo를 fork하세요.
3. index.html 재작성
fork한 repo의 index.html을 본인의 브랜드 페이지로 재작성하세요.
갤러리 바로가기 버튼(<a href="...">)은 삭제하지 마세요.
4. GitHub Pages 활성화
fork한 repo → Settings → Pages → Branch: main / root → Save
본인의 브랜드 페이지가 https://깃허브계정.github.io/mixi-mcp/ 에서 서빙됩니다.
5. 선생님께 전달할 것
추가하고 싶은 MIXI 키워드
갤러리 페이지 스타일 수정 의견
Related MCP server: Scorecard MCP Server
서비스 구조
학생 브랜드 페이지 (GitHub Pages, fork한 repo)
↓ 갤러리 바로가기 버튼
MIXI 갤러리 (https://mixi-mcp.typica-918.workers.dev/gallery)
↑ 폴링
Cloudflare KV (결과 저장)
↑ save_mixi_result
Claude.ai + MIXI 커넥터 (인터뷰 진행)MCP 툴 목록
툴 이름 | 설명 |
| MIXI 브랜드 소개 + 갤러리 안내 + 인터뷰 참여 유도 |
| 인터뷰 진행 (나이 / 성별 / MBTI / 키워드 2개 / 브랜드 3개) |
| 결과를 Cloudflare KV에 저장 |
관리자 가이드 (선생님용)
MIXI 키워드 추가
src/index.ts 상단 배열에 추가 후 push:
const MIXI_KEYWORDS = [
"내추럴 무드",
"모던 미니멀",
"미드센추리",
"추가할 키워드",
];갤러리 스타일 수정
src/index.ts 하단 getGalleryHTML() 함수 내부 CSS 수정 후 push.
push하면 GitHub Actions가 자동으로 Cloudflare Workers에 배포합니다.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceEnables remote control of Lovense toys through Claude using natural language commands. Supports vibration patterns, presets, and intensity control from any device via Cloudflare Workers.4Apache 2.0
- Flicense-qualityCmaintenanceEnables Claude and other MCP-compatible clients to access Scorecard's evaluation tools for running experiments, generating synthetic data, and analyzing model performance. It is designed to be deployed on Cloudflare Workers and integrates securely with Scorecard's API using Clerk for authentication.
- Alicense-qualityDmaintenanceA Cloudflare Worker that provides API access to Postman collections and environments via the Claude AI MCP interface, enabling Claude to assist with API testing, documentation, and management tasks.163ISC
- Alicense-qualityDmaintenanceA minimal, tag-free personal memory system that syncs across all Claude interfaces (mobile, web, desktop, Claude Code). Built on Cloudflare's edge stack for zero-maintenance serverless operation.9MIT
Related MCP Connectors
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Create AI surveys with dynamic follow-up probing directly from your AI assistant.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/caffeineworks-ai/mixi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server