# ONE8943/ai-furniture-hub [Health: Active]

**Category:** 🛒 E-Commerce  
**Repository:** https://github.com/ONE8943/ai-furniture-hub  
**GitHub Stars:** 1  
**npm Downloads (last month):** 342  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/one8943-ai-furniture-hub

## Description
Japan-focused furniture & home product hub for AI agents. 15 tools for mm-precision search across 300+ products and 31 categories, curated sets (bundles, room presets, influencer picks), dimension-compatible replacement finder with fitscore, AI visibility diagnosis, Rakuten live API, and OpenAPI 3.1 schema. Install via npx ai-furniture-hub.

## Tools
Capabilities this server exposes over MCP:

- **search_products** — Search 300+ products by keyword, dimensions (mm), price, color, category, brand
- **get_product_detail** — Full specs: inner dimensions, consumables, compatible storage, curations
- **search_rakuten_products** — Real-time Rakuten Ichiba search (200K+ listings with prices & reviews)
- **search_amazon_products** — Amazon affiliate search URL generation with auto SearchIndex
- **suggest_by_space** — "I have a 600x400mm space" -> everything that fits, rotation-aware
- **identify_product** — Visual description -> product candidates with model numbers
- **coordinate_storage** — Shelf + storage box set proposals: quantity per tier, total cost
- **compare_products** — Side-by-side comparison (2-5 products) on price, size, load, reviews
- **find_replacement** — Discontinued model -> successors + dimension-compatible alternatives with `fit_score
- **calc_room_layout** — Floor-plan rectangle packing with placement coordinates
- **get_related_items** — Accessory chains: required items, protection, consumables, hack substitutes (depth 1-2)
- **get_curated_sets** — Bundles, room presets, influencer picks, hack sets. Filter by type/scene/budget
- **get_popular_products** — Trending products by category with Rakuten data
- **list_categories** — Browse 31 categories with counts, brands, samples
- **diagnose_ai_visibility** — AI visibility audit: llms.txt, robots.txt, JSON-LD, OGP, score 0-100

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "ai-furniture-hub": {
    "command": "npx",
    "args": ["-y","ai-furniture-hub"]
  }
}
```

## Documentation

## What ONE8943/ai-furniture-hub MCP server does

The ONE8943/ai-furniture-hub MCP server helps AI agents search and reason about furniture, storage, appliances, accessories, and other home products for the Japanese market. Its local dataset contains more than 355 curated products across 31 categories and 90-plus brands. Product records can include outer and inner dimensions, prices, colors, brands, load information, compatible storage, consumables, and related items.

The central use case is space-constrained shopping. An agent can search for an item that fits a specified width, depth, or height in millimeters, including cases where rotating the product changes whether it fits. The server also supports coordinated recommendations, such as pairing a shelf with storage boxes, floor protection, cable organizers, or other accessories.

Other workflows cover room layouts, discontinued-product replacements, curated room configurations, influencer selections, budget-oriented hack sets, and product comparisons. The visibility-audit tool evaluates a website’s AI discoverability rather than its furniture catalog.

## How it works

MCP clients can connect over stdio or Streamable HTTP. The hosted endpoint is `https://ai-furniture-hub.onrender.com/mcp`, and the project also publishes a local npm runner. The server exposes 15 tools and three prompts. Tools handle product discovery, detailed records, marketplace searches, comparisons, layout calculations, category browsing, curation, and visibility diagnosis.

Local responses can use mock data, so external API credentials are not required for the basic setup described in the project materials. Marketplace-specific functions include live Rakuten Ichiba search and Amazon affiliate search URL generation. The README also identifies Nitori as an adapter in the architecture, but does not provide a separate Nitori tool in the listed tool table.

Responses include `_attribution` metadata with an `attribution_id`. The project describes this as support for tracking request sources and revenue attribution. It also exposes MCP resources and machine-readable discovery files, including `llms.txt`, full tool schemas, an OpenAPI 3.1 document, and server metadata.

## Setup and configuration

For local stdio use, run `npx ai-furniture-hub`. The repository also supports cloning the project, installing its npm dependencies, and starting it in either stdio or HTTP mode. The local HTTP mode serves MCP at `localhost:3000/mcp`.

A client that accepts remote Streamable HTTP can use the hosted endpoint directly. The README gives examples for Cursor, Claude, VS Code, and ChatGPT-compatible remote MCP configurations. The MCP Registry identifier is `io.github.ONE8943/ai-furniture-hub`.

The documented environment settings include `DEPLOYMENT_MODE`, which selects private or public deployment behavior, and `MCP_API_KEYS_FREE` for configuring free-tier keys.

## Tools and capabilities

The ONE8943/ai-furniture-hub MCP server groups its tools into several practical areas:

- Search products by keyword, dimensions, price, color, category, or brand.
- Retrieve detailed specifications and related product information.
- Search Rakuten listings or generate Amazon affiliate search URLs.
- Find products that fit a defined space and account for rotation.
- Compare two to five products by price, dimensions, load, and reviews.
- Locate replacements and rank dimension-compatible alternatives with a `fit_score` from 0 to 100.
- Calculate room layouts using rectangular floor-plan packing and placement coordinates.
- Build storage combinations, curated sets, room presets, influencer picks, and budget alternatives.
- Diagnose website AI visibility using checks for `llms.txt`, robots rules, JSON-LD, OGP metadata, and related readiness signals.

The three prompts support room coordination, moving checklists, and product showdowns. These workflows turn several tool calls into structured purchasing or comparison tasks.

## Limitations and notes

The catalog is Japan-focused, and live marketplace coverage depends on the relevant adapter or API. Live Rakuten results and attribution behavior may also differ from the mock-data path.

The project publishes both an OpenAPI schema and MCP discovery resources, but the listing does not describe a separate authenticated REST deployment. It also does not state that a paid API key is mandatory. Use the hosted endpoint or npm command according to the client’s MCP transport support, and verify marketplace credentials separately if a live search does not work without them.

_Full upstream README: https://allmcps.com/mcp/one8943-ai-furniture-hub/readme_