ai-furniture-hub
The AI Furniture & Home Product Hub MCP server gives AI agents 15 tools to search, compare, coordinate, and recommend furniture and home products (355+ products, 31 categories, 90+ brands), plus structured prompts and AI visibility diagnostics.
Search & Discovery
search_products: Search by keyword, dimensions (mm), price, color, category, or brandget_product_detail: Full specs — inner dimensions, materials, stock status, consumables, affiliate linkssearch_rakuten_products: Real-time Rakuten Ichiba listings with live prices, reviews, and imagessearch_amazon_products: Generate Amazon affiliate search URLs with automatic category selectionsuggest_by_space: Input room/space dimensions and get all fitting products (rotation-aware)identify_product: Describe visual features to identify model numbers, inner dimensions, and compatible accessories
Coordination & Comparison
coordinate_storage: Propose shelf + storage box combinations with quantity-per-tier and total cost calculationscompare_products: Side-by-side comparison of 2–5 products on price, size, reviews, and load capacityfind_replacement: Find successors/alternatives for discontinued products with afit_score(0–100)calc_room_layout: Simulate furniture placement in a room with coordinates via rectangle packingget_related_items: Discover accessory chains — required accessories, protection materials, and consumables
Curation & Intelligence
get_curated_sets: Browse bundles, room presets, influencer picks, and budget hack sets filtered by type, scene, or budgetget_popular_products: Trending products by category or brand, including Rakuten ranking datalist_categories: All 31 categories with product counts, brand lists, and sample itemsdiagnose_ai_visibility: Audit any website's AI discoverability (checks llms.txt, robots.txt, JSON-LD, OGP tags) — returns a score (0–100), grade (A–F), and recommendations
Structured Prompts
room_coordinator: Full room setup (shelf, boxes, protection) based on space dimensionsmoving_checklist: Room-by-room purchasing checklist based on floor plan typeproduct_showdown: Detailed comparison including accessories and running costs
All results include affiliate URLs for monetization. The server supports MCP (stdio/HTTP), OpenAPI 3.1, Japanese UI, and cross-border readiness checks.
Provides Amazon affiliate search URL generation with auto SearchIndex through the search_amazon_products tool, enabling AI agents to find and recommend Amazon products with affiliate tracking.
Available as an npm package (ai-furniture-hub) for local installation and execution via npx, providing easy distribution and version management through the npm registry.
Enables real-time Rakuten Ichiba search through the search_rakuten_products tool, providing access to 200K+ listings with prices and reviews, and supports Rakuten affiliate integration for revenue attribution.
Supports deployment on Render platform with a hosted endpoint available at https://ai-furniture-hub.onrender.com/mcp for remote MCP connections without local installation.
AI Furniture & Home Product Hub - MCP Server
15 tools | 355+ curated products | 31 categories | 90+ brands Millimeter-precision search, curated sets, AI visibility diagnosis, OpenAPI 3.1 schema. Built for ChatGPT, Claude, Gemini, Cursor, Perplexity, and any MCP-compatible AI agent.
Discovery & Install
MCP Registry name:
io.github.ONE8943/ai-furniture-hubRemote MCP endpoint:
https://ai-furniture-hub.onrender.com/mcpWell-known discovery:
https://ai-furniture-hub.onrender.com/.well-known/mcp.jsonnpm package:
ai-furniture-hub
If your MCP client supports registry search, search for io.github.ONE8943/ai-furniture-hub or AI Furniture & Home Product Hub.
If your client supports direct remote MCP, connect it to https://ai-furniture-hub.onrender.com/mcp.
Related MCP server: KaliCart Global
Why This Exists
AI agents need structured, machine-optimized product data to make useful recommendations. This MCP server provides:
Exact-fit search: "Find a shelf that fits a 425mm gap" returns products with 1mm accuracy
Complete solutions: One search returns the shelf + matching storage boxes + floor protection + cable organizers
Curated by experts: Influencer picks, room presets, bundle deals, and budget hack alternatives
Replacement intelligence: Discontinued product? Get successors ranked by dimension compatibility (fit_score 0-100)
AI visibility consulting: Diagnose any website's AI discoverability with a single tool call
Quick Start
Option 1: Remote (Cursor / Claude / VS Code / ChatGPT)
Connect directly to the hosted server:
{
"mcpServers": {
"furniture-hub": {
"url": "https://ai-furniture-hub.onrender.com/mcp"
}
}
}Works in any MCP client that accepts a remote Streamable HTTP URL.
Option 2: npx (local)
npx ai-furniture-hubOption 3: Clone & Run
git clone https://github.com/ONE8943/ai-furniture-hub.git
cd ai-furniture-hub
npm install
cp .env.example .env # API keys optional - works with mock data
npm start # stdio mode
npm run start:http # HTTP mode at localhost:3000/mcpTools (15)
Search & Discovery
Tool | What It Does |
| Search 300+ products by keyword, dimensions (mm), price, color, category, brand |
| Full specs: inner dimensions, consumables, compatible storage, curations |
| Real-time Rakuten Ichiba search (200K+ listings with prices & reviews) |
| Amazon affiliate search URL generation with auto SearchIndex |
| "I have a 600x400mm space" -> everything that fits, rotation-aware |
| Visual description -> product candidates with model numbers |
Coordination & Comparison
Tool | What It Does |
| Shelf + storage box set proposals: quantity per tier, total cost |
| Side-by-side comparison (2-5 products) on price, size, load, reviews |
| Discontinued model -> successors + dimension-compatible alternatives with |
| Floor-plan rectangle packing with placement coordinates |
| Accessory chains: required items, protection, consumables, hack substitutes (depth 1-2) |
Curation & Intelligence
Tool | What It Does |
| Bundles, room presets, influencer picks, hack sets. Filter by type/scene/budget |
| Trending products by category with Rakuten data |
| Browse 31 categories with counts, brands, samples |
| AI visibility audit: llms.txt, robots.txt, JSON-LD, OGP, score 0-100 |
Prompt Workflows (3)
Prompt | Flow |
| Space dimensions -> shelf + boxes + protection with quantities & cost |
| Floor plan type -> room-by-room purchasing checklist with budget |
| Two products -> full comparison including accessories & running costs |
Product Categories (31)
Area | Categories |
Storage | Shelves, Color boxes, Storage cases, Clothing storage, Steel racks, Closet storage, File storage |
Furniture | Desks, TV stands, Bookshelves, Dining, Sofas & chairs, Bedding |
Room-specific | Kitchen, Laundry, Bath, Entrance, Baby safety |
Hardware | Tension rods, Protection materials, Parts & accessories, Wagons |
Appliances | Home appliances, Kitchen appliances, Air quality, Smart home |
Tech & Lifestyle | PC peripherals, Beauty devices, Gadgets, Health & fitness |
Decor | Curtains & blinds |
Key Features
Cinderella-Fit Search
All 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.
Related-Item Chains
Every 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.
Curated Sets
Bundles: "New Life Starter Kit", "Work From Home Set"
Room Presets: IKEA-style complete room configurations
Influencer Picks: Real recommendations from YouTubers and magazines
Hack Sets: Budget alternatives (100-yen substitutes for 1000-yen accessories)
Dimension-Compatible Replacement
Discontinued product? find_replacement returns:
DB-registered successors
Dimension-compatible alternatives with
fit_score(0-100)Live Rakuten search results
AI Visibility Diagnosis (AIO)
diagnose_ai_visibility audits any URL:
llms.txt presence
robots.txt AI crawler access
Structured data (JSON-LD, Schema.org)
OGP tags
Cross-border readiness (English metadata, multi-currency)
Returns score (0-100), grade (A-F), actionable recommendations
Attribution & Analytics
Every API response includes _attribution metadata with a unique attribution_id, enabling:
Per-call tracking for pay-per-call monetization
Source detection (Apify, RapidAPI, direct)
Contribution logging for revenue attribution
API & Integration
OpenAPI 3.1 Schema
Full OpenAPI spec available at /openapi.yaml for RapidAPI and marketplace integration.
AI Discovery Endpoints
File | URL | Purpose |
llms.txt | AI agent overview | |
llms-full.txt | Full tool schemas & examples | |
OpenAPI | REST API specification | |
Server Card | Machine-readable metadata | |
context.md | Structured AI context | |
robots.txt | AI crawler permissions |
MCP Resources
furniture-hub://llms.txt
furniture-hub://llms-full.txtArchitecture
AI Agent (ChatGPT, Claude, Gemini, Cursor, Perplexity, ...)
| MCP (stdio or Streamable HTTP)
v
+-----------------------------------------------------------+
| 15 Tools + 3 Prompts |
+-----------------------------------------------------------+
| 355+ Products | 31 Categories | 90+ Brands |
| Curated Sets: bundles, room presets, influencer picks |
| Compatibility DB: dimension-based fit scoring |
| Attribution: per-request tracking with attribution_id |
+-----------------------------------------------------------+
| Adapters: Rakuten API / Amazon URL / Nitori |
| Affiliate Engine + Gap Detector + Analytics |
+-----------------------------------------------------------+
|
v
/llms.txt /llms-full.txt /openapi.yaml
/context.md /.well-known/mcp/ /robots.txtEnvironment Variables
Variable | Required | Description |
| No |
|
| No | Comma-separated free-tier API keys for higher rate limits + curated inner dimensions |
| No | Comma-separated pro-tier API keys for unlimited access |
| Render only | Hidden curated inner-dimension DB injected at build time |
| No | Amazon Associate tag |
| No | Rakuten Affiliate ID |
| No | Rakuten API Application ID |
| No |
|
All environment variables are optional. The server works out of the box with mock data.
Deployment
Platform | URL |
MCP Registry |
|
Render |
|
npm |
|
Testing
npm run test:ci # Vitest
npm run test:all # Full legacy suiteContributing
Issues and PRs welcome. See GitHub Issues.
License
MIT
Japanese / 日本語
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。
MCP Registry名:
io.github.ONE8943/ai-furniture-hubリモート接続URL:
https://ai-furniture-hub.onrender.com/mcpwell-known:
https://ai-furniture-hub.onrender.com/.well-known/mcp.json355+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
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
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)
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
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
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
OpenAPI 3.1 - RapidAPI等のマーケットプレイス連携対応
運営
ONE, Inc.
Available Tools
15 toolscalc_room_layout部屋の床面に家具が収まるか簡易シミュレーションA
「この部屋にベッドとデスクは入る?」のように家具の配置可否を確認するときに呼ぶ。部屋の有効寸法(mm)と家具リスト(幅/奥行/個数)からグリッド配置シミュレーションを実行。座標と回転有無を返す。扉・動線は未考慮のため目安として扱うこと。
Inputs: intent (required), room_width_mm (required), room_depth_mm (required), items (required), +3 more.
compare_products製品比較(価格・サイズ・レビュー・耐荷重を並列比較)A
「NクリックとKALLAXどっちがいい?」のように2〜5製品を比較するときに呼ぶ。価格・サイズ・レビュー・耐荷重を並列比較表で返す。カタログ一致時は内寸・互換収納・buy_guide(best_for/avoid_if)も付加。buy_guideのdecision_hintは比較recommendationにも反映済み。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), keywords (required), compare_aspects.
coordinate_storage棚+収納ボックスのコーディネート提案(個数計算付き)A
「この棚に合うボックスは?」「カラーボックスの整理方法」のときに呼ぶ。棚の内寸から収納ボックスの入り数を計算し、1段あたり何個×全段=合計個数・合計金額を算出。設置場所(押入れ/洗面所/キッチン等)に応じたコーディネートのコツ+ペルソナ別推薦(persona_hints)も提供。persona_hintsには予算・おすすめブランド・タイプ別アドバイスが含まれるのでユーザーに合った提案に活用。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), keyword (required), price_max, storage_keyword, +2 more.
diagnose_ai_visibilityAI可視性診断(AIO診断)A
URLを指定すると、そのサイトがAIエージェント(GPT/Claude/Gemini等)からどの程度「見えている」かを診断する。llms.txt、robots.txt(AIクローラー許可)、構造化データ(JSON-LD)、OGPメタタグ、寸法データ表記、越境対応度をチェックし、0-100のスコアとA-Fグレードを返す。越境対応度(cross_border_readiness)は海外AIエージェントへの可視性を評価。AIOエージェンシーのデモとして「御社の商品、AIからこう見えています」と提示できる。
Inputs: intent (required), url (required).
find_replacement廃番・旧型の後継・代替品を探すA
「この型番が売ってない」「生産終了した棚の代わり」のときに呼ぶ。カタログの後継候補(successors)と楽天の「後継」「新型」検索結果を返す。最終確認はメーカー公式で。楽天候補のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), query (required).
get_curated_setsキュレーション済みセット提案(バンドル/ルームプリセット/インフルエンサーPick/ハックセット)A
「新生活に必要なもの一式」「YouTuberのデスクツアーで紹介された商品」「予算5万で書斎を作りたい」のようなセット提案・キュレーション情報を返す。バンドル(まとめ買いセット)、ルームプリセット(IKEA式ルームセット)、インフルエンサーPick(専門家・YouTuber・雑誌編集部のおすすめ)、ハックセット(代用品セット)の4種類。各商品のproduct_idsでget_product_detailやsearch_rakuten_productsを呼べば詳細と購入リンクが得られる。
Inputs: intent (required), type, scene, occasion, +2 more.
get_popular_products人気・おすすめ製品(カテゴリ/ブランド別)A
「おすすめの棚は?」「人気のキッチン家電は?」のときに呼ぶ。カテゴリ/ブランドで絞って、互換収納・消耗品情報が充実したおすすめ製品を返す。楽天のレビュー数トレンドも付加。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), category, brand, limit, +1 more.
get_product_detail家具・収納商品の詳細情報を取得A
商品IDを指定して、特定の家具・収納商品のフルスペック(寸法・価格・在庫・素材など)を取得します。【重要】intentには、なぜこの詳細が必要か(例:購入前の最終確認、サイズの詳細確認、他商品との比較)を記述してください。【収益化】返却される affiliate_url をユーザーへの購入リンクとして使用してください。関連商品(同シリーズ・近いサイズ)も自動で提案されます。
Inputs: id (required), intent (required).
identify_product写真・特徴テキストから製品を特定(型番・内寸・消耗品情報付き)A
「この写真の棚は何?」「持ってる棚に合うボックスを知りたい」のときに呼ぶ。Vision AIで画像から抽出した特徴テキスト(ブランド/色/段数/素材/推定サイズ)を渡すと、カタログ+楽天から候補を返す。型番特定時は内寸・消耗品・互換ボックス情報付き。
Inputs: intent (required), features (required), brand_hint, dimensions_hint, +1 more.
list_categories製品カテゴリ一覧A
「何が検索できる?」「どんなカテゴリがある?」のときに呼ぶ入口ツール。全31カテゴリと製品数・取扱ブランドを返す。カテゴリ名指定でそのカテゴリの製品一覧も取得可能。まずこのツールでカテゴリを把握→ユーザーに提示→選んだカテゴリでsearch_productsに進む。
Inputs: intent (required), category_filter.
search_amazon_productsAmazonで家具・収納商品を検索(URL生成)A
ユーザーがAmazonで買いたい場合や楽天で見つからない場合に呼ぶ。Amazonの検索結果ページへのアフィリエイトURLを生成する(商品データは返さない)。SearchIndexはカテゴリから自動選択。affiliate_urlをユーザーに提示すること。
Inputs: intent (required), keyword (required), price_min, price_max, +1 more.
search_products家具・家電・ガジェット商品を検索A
ユーザーが「棚が欲しい」「Dysonのドライヤー」「幅40cmに入るもの」と言ったときに呼ぶ。31カテゴリ・80+ブランドのカタログをキーワード・サイズ(mm)・価格・色・ブランドで横断検索。結果にrelated_items_hintがある場合はget_related_itemsで付属品チェーンを取得できる。buy_guideがある場合はbest_for/avoid_ifをユーザーに伝えて購入判断を助けること。seasonal_hints/active_salesがある場合はセール情報を伝えること。色はエイリアス対応(白→ホワイト/アイボリー等)。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), keyword, width_mm_min, width_mm_max, +10 more.
search_rakuten_products楽天市場から家具・収納商品を検索A
カタログにない商品や最新価格・在庫が必要なときに呼ぶ。楽天市場APIでリアルタイム検索し、価格・レビュー・画像付きで返す。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), keyword (required), price_min, price_max, +2 more.
suggest_by_space空きスペースに入る製品をカテゴリ横断で提案A
「洗面所の幅45cm×奥行30cmの隙間に何か置きたい」のようにスペース起点で探すときに呼ぶ。寸法(mm)を指定すると、そこに収まる製品をカテゴリ横断で返す。回転フィット対応(幅と奥行を入れ替えても判定)。棚+ボックスの両方が見つかればコーディネーションプランも自動生成。各商品のaffiliate_urlをユーザーに提示すること。
Inputs: intent (required), width_mm (required), depth_mm (required), height_mm (required), +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
The tools have distinct primary purposes, but there is notable overlap in search and recommendation functions. For example, search_products, search_rakuten_products, and search_amazon_products all handle product searches across different platforms, while get_popular_products and get_curated_sets both provide recommendations, which could cause confusion in tool selection. Descriptions help clarify, but the boundaries are not always sharp.
Most tools follow a consistent verb_noun naming pattern (e.g., calc_room_layout, compare_products, get_product_detail), which aids predictability. However, there are minor deviations like diagnose_ai_visibility and identify_product, which use different verb styles or compound terms, slightly breaking the pattern but remaining readable overall.
With 15 tools, the server is well-scoped for its furniture and home goods domain, covering aspects like layout calculation, product search, comparison, recommendations, and diagnostics. Each tool appears to serve a specific function without redundancy, making the count appropriate for the intended purpose.
The toolset provides comprehensive coverage for furniture and home goods, including search, comparison, recommendations, layout planning, and product identification. Minor gaps exist, such as no explicit tools for user account management or order tracking, but these are not core to the domain, and agents can work around them with the available tools.
Related MCP Connectors
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
An MCP server that audits the fairness of construction and renovation estimates in Japan. Provides fair-price ranges, overcharge detection, and verifiable unit-cost data based on JCCDB (65,520 items across 402 categories, CC BY 4.0, DOI-backed).
Pocket Agent (aipocketagent.com) MCP server — read tools for personas, apps, and product info.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceMCP server to search Rakuten Ichiba (Japan's largest e-commerce platform) for products, returning names, prices, URLs, shop info, reviews, and images via the official Rakuten API.-
- AlicenseNot gradedqualityCmaintenanceFederated commerce search MCP server enabling AI agents to query real product offers, prices, and availability across independent WooCommerce stores without API keys or registration.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables AI shopping assistants to understand customer needs, search products using visual and semantic queries, apply metadata filters, and recommend relevant products from an inventory.2Apache 2.0
- AlicenseAqualityDmaintenanceA local AI shopping MCP server for Amazon.co.jp that searches products, adds them to cart, and opens the review page without automating purchase confirmation. It keeps your Amazon login confined to your machine's Chrome profile.5MIT