Japan Car Market Mcp

io.github.atushi1841Published by GitHub account atushi1841v1.0.0Updated Nov 2, 2026

Japan used car prices from goo-net.com via Apify + Gumroad

VerifiedSTDIODesktop onlyWeb Search & ScrapingFinance

Overview

AI-generated overview

Scrapes goo-net.com used car listings in Japan, giving an assistant car titles, makers, JPY prices, dealer shops and detail links, plus price statistics.

What you can do
  • Search used car listings by model or brand keyword, optionally limited to one of Japan's 47 prefectures
  • Retrieve listing details per car: title, maker, price in JPY, image URL, dealer shop and detail page link
  • Return aggregated price statistics (count, min, max, average, median) for a model instead of full listings
  • Control crawl size with maximum items and maximum pages settings
When to use it
Useful for used car exporters, importers and market researchers who need current Japanese used car inventory and pricing, or for JDM enthusiasts tracking specific models. It suits price benchmarking and market trend work rather than general web research.
Requirements
Runs as a local process (stdio) on the desktop; the README shows a Python 3.11 setup and also mentions an Apify actor and Smithery install. Scraping runs through Apify, which requires an Apify account and API token, and results are billed per item.
Before you install
Paid usage: the README states $0.002 per item ($2 per 1,000 listings), billed through Apify, and an Apify API token is needed. It scrapes a third-party site, so goo-net's terms and robots.txt should be checked before commercial use. Requests are routed through Apify proxy.

Installation

In SourceWeft

  1. Open Japan Car Market Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Goo-net Japan Used Cars Scraper

Scrape used car listings from goo-net.com — one of Japan's largest used car portals — with prices, maker, and dealer information.

Why This Data

  • Japan exported a record 1.71 million used vehicles in 2025 (JUMVEA) — a massive global market
  • Used car exporters (BE FORWARD, carused.jp, SBT Japan, etc.) constantly need fresh inventory and pricing data
  • JDM (Japanese Domestic Market) models are highly valued worldwide
  • Zero dedicated cross-listing competitor on Apify Store at launch

Features

  • ✅ Server-side rendered pages (no browser needed — fast & cheap)
  • ✅ Nationwide inventory (47 prefectures) with pagination
  • ✅ Model name, price (JPY), maker, image, dealer shop, and detail URL per listing
  • ✅ Prefecture filter (e.g. 01 = Hokkaido, 13 = Tokyo, 47 = Okinawa)
  • ✅ EUC-JP encoding handled automatically
  • ✅ Runs on Apify proxy — no IP blocking issues

Input

FieldTypeDefaultDescription
searchKeywordstringemptyCar model / brand keyword (e.g. ハイエース, アクア). Empty = full scan
statsModebooleanfalsetrue = return aggregated price stats instead of listings
statsKeywordstringemptyModel name to aggregate (e.g. N-BOX, ハイエース)
prefecturestringemptyPrefecture code 01–47. Empty = all Japan
maxItemsinteger100Maximum number of listings to collect
maxPagesinteger5Maximum number of pages to crawl
proxyConfigurationobjectautoApify proxy (auto)

Output

Each item contains: itemId, title, maker, price (JPY), imageUrl, detailUrl, shop, source, scrapedAt.

Example:

json
{  "itemId": "988026080400207235003",  "title": "ハイエースバン スーパーGL",  "maker": "トヨタ",  "price": 2796000,  "detailUrl": "https://www.goo-net.com/usedcar/spread/goo/15/988026080400207235003.html",  "shop": "ハイエース／キャラバン専門店 ファイントラスト土岐店",  "source": "goo-net"}

Use Cases

  • 🚗 Used car exporters & importers (inventory tracking, pricing research)
  • 📊 Market researchers (JDM market trends, price analysis)
  • 🔍 JDM enthusiasts hunting specific models

Price Stats API Mode (相場統計API)

Same Actor doubles as a price stats API for market research — returns aggregated price statistics for a car model without downloading the full listing data.

Request (Apify synchronous API):

bash
curl -X POST "https://api.apify.com/v2/acts/bgm5Gxn4BeBmoO7xD/run-sync-get-dataset-items?token=YOUR_TOKEN&timeout=120" \  -H "Content-Type: application/json" \  -d '{"statsMode": true, "statsKeyword": "N-BOX", "maxItems": 30, "maxPages": 1}'

Response (JSON):

json
{  "statsType": "goo-net-car-price",  "keyword": "N-BOX",  "count": 5,  "priceMin": 230000,  "priceMax": 1907000,  "priceAvg": 974400,  "priceMedian": 596000,  "sampleItems": [{"title": "...", "price": 230000, "detailUrl": "...", "shop": "..."}]}
  • statsKeyword: model name (e.g. N-BOX, ハイエース). Full-width/half-width matching handled automatically
  • Combine with bodyType to narrow (e.g. KEI, SUV)
  • Use cases: market research, dealer pricing benchmarks, export valuation

Pricing

Pay per result: $0.002 per item ($2 per 1,000 listings).

Legal

  • Respects goo-net's robots.txt (search endpoints excluded; category pages allowed)
  • For research and legitimate business use. Check goo-net's terms before commercial use.
  • Rate-limited by design (3 retries, exponential backoff).

Tech

  • Python 3.11 + httpx + BeautifulSoup
  • Apify Actor SDK v3
  • EUC-JP decode support

MCP Server & Registry

This scraper is also available as an MCP server for AI agents:

Install via MCP: add to your MCP config:

json
{"mcpServers": {"japan-car-market-mcp": {"command": "python3", "args": ["src/stdio_main.py"]}}}

Smithery

[Smithery]

Install via Smithery:

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

Source: README.md at commit 84082ea

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestOct 19, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.