MCP server: One MCP server.

Japan Market

@atushi1841MCP server · External

Compare used-good prices across 9 Japanese shops + Rakuten Ichiba, MAFF data, prize giveaways.

Price comparisonv0.1.0Python
Freeno charge per call

Runs on your machine from its package; the steps are below.

What it does

  1. Reads
  2. Writes
  3. High impact

At most: only reads or looks up information.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

MCP Bundlehttps://github.com/atushi1841/japan-market-mcp/releases/download/v0.1.0/japan-market-mcp.mcpbv0.1.0

Distributed as an MCP bundle (`https://github.com/atushi1841/japan-market-mcp/releases/download/v0.1.0/japan-market-mcp.mcpb`) — download it and import the bundle in your MCP client.

README7 min read

Japan Market MCP — Cross-Shop Price Comparison for AI Agents

An MCP server that lets AI agents (Claude, Cursor, VS Code Copilot, ChatGPT) compare used-good prices across leading Japanese shops in a single tool call. Instead of scraping site by site, an agent queries one server and gets inter-store price gaps for the same product — perfect for reseller arbitrage, price monitoring, and market research on the Japanese second-hand market.

How it works

The server wraps market-scraping and official-API actors (Rakuten Ichiba included) behind one MCP endpoint. Each tool returns price, brand, shop, condition and a link per item, with the shop-pair crossed so you see the price spread at a glance.

Available tools

ToolMarketShop pair
search_camera_marketUsed cameras & lensesKitamura + Fujiya Camera
search_watch_marketLuxury watchesJackroad + Kitamura used watches
search_luxury_marketUsed luxury brandsKomehyo + Jackroad
search_instrument_marketUsed instrumentsDigimart + Ishibashi U-BOX
search_offmall_marketGeneral used goodsOffMall (Hard Off official, 800+ stores)
search_kakaku_pricesNew price comparisonKakaku.com (aggregated, thousands of shops)
search_car_marketUsed carsgoo-net (nationwide, by body type)
search_car_price_statsUsed car price stats (min/max/avg/median JPY)goo-net (by model keyword, e.g. N-BOX, Alphard)
search_japan_prize_giveawaysCurrent JP prize giveaways with deadlines (懸賞/プレゼント)kenshou.club + cp.meikan.org
get_japan_prize_giveaway_statsAggregate giveaway stats (counts, active, winners)kenshou.club + cp.meikan.org
search_rakuten_itemsNew retail products (official API)Rakuten Ichiba 楽天市場 (keyword, price range, sort)
get_rakuten_rankingBest-seller ranking (official API)Rakuten Ichiba 楽天市場 (overall or by genre)
get_maff_market_reportFresh produce wholesale market report (official MAFF open data)Japan central markets (旬別, JPY/100kg, YoY%)
search_maff_price_trendFresh produce wholesale price trend (official MAFF open data)Multi-market, multi-period comparison
get_maff_top_moversFresh produce YoY price movers (official MAFF open data)Japan central markets (supply-shock signal)
get_maff_marketsList available MAFF wholesale marketsno charge

Each tool takes a keyword (e.g. SONY α7, ROLEX, Hermes, Fender) and returns results from the crossed shops. Leaving the keyword empty scans the full category.

Pricing

Pay per event — $0.001 per search + actor start fee. Runs finish in seconds, so a full keyword lookup typically costs well under $0.01.

Connect as an MCP server

Run it from the Apify Store (Run button), then point your MCP client at the endpoint. It stays in standby mode.

MCP client config (Claude Desktop / Cursor / VS Code):

json
{
  "mcpServers": {
    "japan-market-mcp": {
      "url": "https://fruitful-quintessence--japan-market-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}
  • URL: <your-username>--japan-market-mcp.apify.actor/mcp
  • Auth: Apify API token in the Authorization: Bearer header (Apify Console → Settings → Integrations)

URL note: use a hyphen in the username (fruitful-quintessence), not an underscore — an underscore hostname will not resolve.

Discovery & registry

  • Agent install guide: see llms-install.md — grounded guidance for AI agents (Cline, Claude Code, Cursor) that set up this server for a user.
  • MCP discovery manifest: .well-known/mcp.json advertises the endpoint, auth, tool list, and pricing in the standard MCP Directory discovery format.
  • Cline MCP Marketplace: submitted for review at cline/mcp-marketplace — once approved it becomes one-click installable from Cline's marketplace.
  • Apify Store: deployed as the public actor fruitful_quintessence/japan-market-mcp (pay-per-event).

This MCP server connects to 86+ Apify Actors in the Kensho ecosystem for real-time data. Key related actors include:

Marketplace & Price Comparison

Retail & E-commerce

Used Goods & Auctions

Local Business & Services

Government & Public Data

Specialized Collections

MCP Connection Examples

6. External run example (fallback)

bash
# If GitHub API returns 403, use curl + git clone
curl -s https://raw.githubusercontent.com/atushi1841/japan-market-mcp/main/README.md > README.patch
# edit README.patch as needed
git clone https://github.com/atushi1841/japan-market-mcp.git
cd japan-market-mcp
cp ../README.patch README.md
git add README.md
git commit -m "update README via external run"
git push

1. Standard I/O (stdio) — Claude Desktop, Cursor, etc.

In your claude_desktop_config.json:

json
{
  "mcpServers": {
    "japan-market-mcp": {
      "command": "python",
      "args": ["-m", "src.main"]
    }
  }
}

2. HTTP Server Mode

bash
# Install dependencies
pip install -r requirements.txt

# Run as HTTP server on port 3000
APIFY_TOKEN=your_token python -m src.main --http --port 3000

# Test the endpoint
curl http://localhost:3000/mcp/tools | jq .

3. Direct Python Import

python
from src.main import mcp
# FastMCP instance can be embedded directly

4. n8n / Apify Workflow (via HTTP)

Use Apify's Webhook node to POST JSON-RPC to POST /mcp endpoint.

5. Docker Deployment

bash
docker build -t japan-market-mcp .
docker run -p 3000:3000 -e APIFY_TOKEN=your_token japan-market-mcp
"Compare used prices for Sony a7 III between Kitamura and Fujiya"
→ search_camera_market(keyword="SONY α7 III")

"What's the inter-store price gap for a Rolex Submariner?"
→ search_watch_market(keyword="ROLEX Submariner")

"What's the market price for a Hermes Birkin 25?"
→ search_luxury_market(keyword="Hermes Birkin 25")

"What's a used Fender Stratocaster going for?"
→ search_instrument_market(keyword="Fender Stratocaster")

"Show this 旬's wholesale market report for Tokyo (Toyosu) fresh vegetables"
→ get_maff_market_report(market="toyosu")

"Which fresh produce items have spiked in price vs last year at Osaka?"
→ get_maff_top_movers(market="oosakaho")

"Track the price of daikon (だいこん) across Tokyo and Osaka this month"
→ search_maff_price_trend(item="だいこん", markets=["toyosu","oosakaho"])

Use cases

  • Reseller arbitrage — spot the same product priced differently across shops
  • Market research — track used prices for cameras, watches, luxury goods, instruments, cars
  • Export sourcing — goo-net JDM inventory and goo-net price checks for exporters
  • Collector price checks — condition-ranked physical used items from OffMall

Data sources

  • Each actor collects factual data only (product name, price, brand, condition, inventory, URL). No photos or descriptions are harvested.
  • All target sites allow crawling via their robots.txt.
  • MAFF 青果物卸売市場調査(旬別・市場別) is served from the official 農林水産省 open-data CSV — no scraping, direct download. Published under the Government Standard Terms of Use v2.0 (政府標準利用規約2.0): commercial use allowed with attribution. Price is JPY per 100kg. Data updates are published by MAFF each 旬 (10-day period).

Local development

bash
pip install -r requirements.txt
APIFY_TOKEN=apify_api_xxx python -m src.main
# Streamable HTTP endpoint at http://localhost:3000/mcp

License

MIT

Install via Smithery

Connect this MCP server to your AI client (Claude Desktop, Cursor, VS Code) in one command:

bash
npx @smithery/cli install atushi1841/japan-market-mcp --client claude

Replace claude with cursor, vscode, or cline for other clients.

Alternatively, install directly from the Smithery registry.

Note: Smithery server listing is pending verification. Once verified, this server will appear in search results with useCount tracking.

Similar modules

Browse Price comparison