{
  "markdown": "# AI Furniture & Home Product Hub - MCP Server\n\n> **15 tools** | **355+ curated products** | **31 categories** | **90+ brands**\n> Millimeter-precision search, curated sets, AI visibility diagnosis, OpenAPI 3.1 schema.\n> Built for ChatGPT, Claude, Gemini, Cursor, Perplexity, and any MCP-compatible AI agent.\n\n[![CI](https://github.com/ONE8943/ai-furniture-hub/actions/workflows/ci.yml/badge.svg)](https://github.com/ONE8943/ai-furniture-hub/actions/workflows/ci.yml)\n[![npm](https://img.shields.io/npm/v/ai-furniture-hub)](https://www.npmjs.com/package/ai-furniture-hub)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n## Discovery & Install\n\n- **MCP Registry name**: `io.github.ONE8943/ai-furniture-hub`\n- **Remote MCP endpoint**: `https://ai-furniture-hub.onrender.com/mcp`\n- **Well-known discovery**: `https://ai-furniture-hub.onrender.com/.well-known/mcp.json`\n- **npm package**: [`ai-furniture-hub`](https://www.npmjs.com/package/ai-furniture-hub)\n\nIf your MCP client supports registry search, search for `io.github.ONE8943/ai-furniture-hub` or `AI Furniture & Home Product Hub`.\nIf your client supports direct remote MCP, connect it to `https://ai-furniture-hub.onrender.com/mcp`.\n\n## Why This Exists\n\nAI agents need structured, machine-optimized product data to make useful recommendations. This MCP server provides:\n\n- **Exact-fit search**: \"Find a shelf that fits a 425mm gap\" returns products with 1mm accuracy\n- **Complete solutions**: One search returns the shelf + matching storage boxes + floor protection + cable organizers\n- **Curated by experts**: Influencer picks, room presets, bundle deals, and budget hack alternatives\n- **Replacement intelligence**: Discontinued product? Get successors ranked by dimension compatibility (fit_score 0-100)\n- **AI visibility consulting**: Diagnose any website's AI discoverability with a single tool call\n\n## Quick Start\n\n### Option 1: Remote (Cursor / Claude / VS Code / ChatGPT)\n\nConnect directly to the hosted server:\n\n```json\n{\n  \"mcpServers\": {\n    \"furniture-hub\": {\n      \"url\": \"https://ai-furniture-hub.onrender.com/mcp\"\n    }\n  }\n}\n```\n\nWorks in any MCP client that accepts a remote Streamable HTTP URL.\n\n### Option 2: npx (local)\n\n```bash\nnpx ai-furniture-hub\n```\n\n### Option 3: Clone & Run\n\n```bash\ngit clone https://github.com/ONE8943/ai-furniture-hub.git\ncd ai-furniture-hub\nnpm install\ncp .env.example .env   # API keys optional - works with mock data\nnpm start               # stdio mode\nnpm run start:http      # HTTP mode at localhost:3000/mcp\n```\n\n## Tools (15)\n\n### Search & Discovery\n\n| Tool | What It Does |\n|------|-------------|\n| `search_products` | Search 300+ products by keyword, dimensions (mm), price, color, category, brand |\n| `get_product_detail` | Full specs: inner dimensions, consumables, compatible storage, curations |\n| `search_rakuten_products` | Real-time Rakuten Ichiba search (200K+ listings with prices & reviews) |\n| `search_amazon_products` | Amazon affiliate search URL generation with auto SearchIndex |\n| `suggest_by_space` | \"I have a 600x400mm space\" -> everything that fits, rotation-aware |\n| `identify_product` | Visual description -> product candidates with model numbers |\n\n### Coordination & Comparison\n\n| Tool | What It Does |\n|------|-------------|\n| `coordinate_storage` | Shelf + storage box set proposals: quantity per tier, total cost |\n| `compare_products` | Side-by-side comparison (2-5 products) on price, size, load, reviews |\n| `find_replacement` | Discontinued model -> successors + dimension-compatible alternatives with `fit_score` |\n| `calc_room_layout` | Floor-plan rectangle packing with placement coordinates |\n| `get_related_items` | Accessory chains: required items, protection, consumables, hack substitutes (depth 1-2) |\n\n### Curation & Intelligence\n\n| Tool | What It Does |\n|------|-------------|\n| `get_curated_sets` | Bundles, room presets, influencer picks, hack sets. Filter by type/scene/budget |\n| `get_popular_products` | Trending products by category with Rakuten data |\n| `list_categories` | Browse 31 categories with counts, brands, samples |\n| `diagnose_ai_visibility` | AI visibility audit: llms.txt, robots.txt, JSON-LD, OGP, score 0-100 |\n\n### Prompt Workflows (3)\n\n| Prompt | Flow |\n|--------|------|\n| `room_coordinator` | Space dimensions -> shelf + boxes + protection with quantities & cost |\n| `moving_checklist` | Floor plan type -> room-by-room purchasing checklist with budget |\n| `product_showdown` | Two products -> full comparison including accessories & running costs |\n\n## Product Categories (31)\n\n| Area | Categories |\n|------|-----------|\n| **Storage** | Shelves, Color boxes, Storage cases, Clothing storage, Steel racks, Closet storage, File storage |\n| **Furniture** | Desks, TV stands, Bookshelves, Dining, Sofas & chairs, Bedding |\n| **Room-specific** | Kitchen, Laundry, Bath, Entrance, Baby safety |\n| **Hardware** | Tension rods, Protection materials, Parts & accessories, Wagons |\n| **Appliances** | Home appliances, Kitchen appliances, Air quality, Smart home |\n| **Tech & Lifestyle** | PC peripherals, Beauty devices, Gadgets, Health & fitness |\n| **Decor** | Curtains & blinds |\n\n## Key Features\n\n### Cinderella-Fit Search\nAll dimensions in millimeters - outer AND inner. Find products that fit a specific space with 1mm tolerance. Rotation-aware: automatically checks if swapping width/depth creates a fit.\n\n### Related-Item Chains\nEvery product links to 3-5 related items: required accessories (HEPA filters for air purifiers), protection materials (floor mats for heavy shelves), consumables (vacuum bags), compatible storage boxes.\n\n### Curated Sets\n- **Bundles**: \"New Life Starter Kit\", \"Work From Home Set\"\n- **Room Presets**: IKEA-style complete room configurations\n- **Influencer Picks**: Real recommendations from YouTubers and magazines\n- **Hack Sets**: Budget alternatives (100-yen substitutes for 1000-yen accessories)\n\n### Dimension-Compatible Replacement\nDiscontinued product? `find_replacement` returns:\n- DB-registered successors\n- Dimension-compatible alternatives with `fit_score` (0-100)\n- Live Rakuten search results\n\n### AI Visibility Diagnosis (AIO)\n`diagnose_ai_visibility` audits any URL:\n- llms.txt presence\n- robots.txt AI crawler access\n- Structured data (JSON-LD, Schema.org)\n- OGP tags\n- Cross-border readiness (English metadata, multi-currency)\n- Returns score (0-100), grade (A-F), actionable recommendations\n\n### Attribution & Analytics\nEvery API response includes `_attribution` metadata with a unique `attribution_id`, enabling:\n- Per-call tracking for pay-per-call monetization\n- Source detection (Apify, RapidAPI, direct)\n- Contribution logging for revenue attribution\n\n## API & Integration\n\n### OpenAPI 3.1 Schema\nFull OpenAPI spec available at [`/openapi.yaml`](https://ai-furniture-hub.onrender.com/openapi.yaml) for RapidAPI and marketplace integration.\n\n### AI Discovery Endpoints\n\n| File | URL | Purpose |\n|------|-----|---------|\n| llms.txt | [/llms.txt](https://ai-furniture-hub.onrender.com/llms.txt) | AI agent overview |\n| llms-full.txt | [/llms-full.txt](https://ai-furniture-hub.onrender.com/llms-full.txt) | Full tool schemas & examples |\n| OpenAPI | [/openapi.yaml](https://ai-furniture-hub.onrender.com/openapi.yaml) | REST API specification |\n| Server Card | [/.well-known/mcp/server-card.json](https://ai-furniture-hub.onrender.com/.well-known/mcp/server-card.json) | Machine-readable metadata |\n| context.md | [/context.md](https://ai-furniture-hub.onrender.com/context.md) | Structured AI context |\n| robots.txt | [/robots.txt](https://ai-furniture-hub.onrender.com/robots.txt) | AI crawler permissions |\n\n### MCP Resources\n```\nfurniture-hub://llms.txt\nfurniture-hub://llms-full.txt\n```\n\n## Architecture\n\n```\nAI Agent (ChatGPT, Claude, Gemini, Cursor, Perplexity, ...)\n    | MCP (stdio or Streamable HTTP)\n    v\n+-----------------------------------------------------------+\n|  15 Tools + 3 Prompts                                     |\n+-----------------------------------------------------------+\n|  355+ Products | 31 Categories | 90+ Brands               |\n|  Curated Sets: bundles, room presets, influencer picks     |\n|  Compatibility DB: dimension-based fit scoring             |\n|  Attribution: per-request tracking with attribution_id     |\n+-----------------------------------------------------------+\n|  Adapters: Rakuten API / Amazon URL / Nitori               |\n|  Affiliate Engine + Gap Detector + Analytics               |\n+-----------------------------------------------------------+\n    |\n    v\n  /llms.txt        /llms-full.txt        /openapi.yaml\n  /context.md      /.well-known/mcp/     /robots.txt\n```\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `DEPLOYMENT_MODE` | No | `private` (default, affiliate ON) or `public` (affiliate OFF for marketplace) |\n| `MCP_API_KEYS_FREE` | No | Comma-separated free-tier API keys for higher rate limits + curated inner dimensions |\n| `MCP_API_KEYS_PRO` | No | Comma-separated pro-tier API keys for unlimited access |\n| `INNER_DIMENSIONS_DATA` | Render only | Hidden curated inner-dimension DB injected at build time |\n| `AFFILIATE_ID_AMAZON` | No | Amazon Associate tag |\n| `AFFILIATE_ID_RAKUTEN` | No | Rakuten Affiliate ID |\n| `RAKUTEN_APP_ID` | No | Rakuten API Application ID |\n| `RAKUTEN_API_MOCK` | No | `true` (default) for mock data, `false` for live |\n\nAll environment variables are optional. The server works out of the box with mock data.\n\n## Deployment\n\n| Platform | URL |\n|----------|-----|\n| **MCP Registry** | `io.github.ONE8943/ai-furniture-hub` |\n| **Render** | `https://ai-furniture-hub.onrender.com/mcp` |\n| **npm** | `npx ai-furniture-hub` |\n\n## Testing\n\n```bash\nnpm run test:ci      # Vitest\nnpm run test:all     # Full legacy suite\n```\n\n## Contributing\n\nIssues and PRs welcome. See [GitHub Issues](https://github.com/ONE8943/ai-furniture-hub/issues).\n\n## License\n\nMIT\n\n---\n\n## Japanese / 日本語\n\n**AI Furniture & Home Product Hub** は家具・家電・ガジェット等のAIエージェント向けMCPサーバーです。\n\n- **MCP Registry名**: `io.github.ONE8943/ai-furniture-hub`\n- **リモート接続URL**: `https://ai-furniture-hub.onrender.com/mcp`\n- **well-known**: `https://ai-furniture-hub.onrender.com/.well-known/mcp.json`\n\n- **355+商品、31カテゴリ、90+ブランド** のキュレーション済みカタログ\n- **mm精度の寸法検索** - 「幅425mmの隙間にぴったり収まる棚」を即座に発見\n- **関連アイテムチェーン** - 1商品から3-5個の関連商品（必須アクセサリ、保護材、消耗品）\n- **キュレーション** - バンドル提案、ルームプリセット、インフルエンサーおすすめ、100均代用ハック\n- **後継品検索** - 廃番商品から寸法互換の代替品をfit_scoreで提案\n- **AI可視性診断（AIO）** - Webサイトの「AIからの見え方」を0-100でスコアリング\n- **OpenAPI 3.1** - RapidAPI等のマーケットプレイス連携対応\n\n### 運営\n\nONE, Inc.\n",
  "bytes": 10647,
  "sha": "6e6fb943004b4d69dfec91eaae63c284389757693546e7354c955bea41c552f0",
  "repo_slug": "one8943/ai-furniture-hub",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_one8943_ai_furniture_hub_ff31ffbe/readme"
}