About mandarake-surugaya-mcp
mandarake-surugaya-mcp is an MCP server for AI agents researching Japanese collectibles. It searches Mandarake auctions, Suruga-ya prices and Rakuten Ichiba, with a tool to compare prices across the three marketplaces.
Key features
- 01Mandarake auction keyword search
- 02Suruga-ya product price search
- 03Rakuten Ichiba product search
- 04Cross-marketplace price comparison
Use cases
- 01Check current collectible prices across marketplaces
- 02Compare prices before buying or reselling
MCP support
Exposes search tools for Mandarake auctions, Suruga-ya and Rakuten Ichiba, plus cross-marketplace price comparison to MCP clients. Supports Streamable HTTP and SSE.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMandarake & Suruga-ya MCP Server
An MCP server that gives AI agents real-time access to Mandarake auction and Suruga-ya price data for Japanese collectibles. Connect from Claude Desktop, Claude Code, ChatGPT, Cursor, or any MCP client.
まんだらけオークションと駿河屋の中古ホビー価格をAIエージェントからリアルタイム検索できるMCPサーバー。
Tools
| Tool | Description | Price |
|---|---|---|
search_mandarake_auction | Search Mandarake auction listings by keyword | $0.001/call |
search_surugaya | Search Suruga-ya product prices by keyword | $0.001/call |
search_rakuten | Search Rakuten Ichiba products via official API | $0.001/call |
compare_prices | Cross-reference prices across Suruga-ya, Mandarake, and Rakuten | $0.001/call |
get_actor_info | List available tools and usage info | Free |
Quick Start
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"mandarake-surugaya": {
"url": "https://fruitful-quintessence--mandarake-surugaya-mcp.apify.actor/mcp"
}
}
}
Claude Code
claude mcp add mandarake-surugaya \
--transport http \
https://fruitful-quintessence--mandarake-surugaya-mcp.apify.actor/mcp
Any MCP Client (Streamable HTTP)
Endpoint: https://fruitful-quintessence--mandarake-surugaya-mcp.apify.actor/mcp
Output Sample
Tool: search_mandarake_auction("フィギュア")
Results:
1. ドラゴンボール フィギュア | ¥3,000 | 5 bids | 12 watchers | まんだらけ 中野店
2. ワンピース フィギュア | ¥2,500 | 3 bids | 8 watchers | まんだらけ 渋谷店
Tool: search_surugaya("フィギュア ドラゴンボール")
Results:
1. ドラゴンボールZ フィギュア | Used: ¥3,500 | List: ¥5,000 | In stock
2. ドラゴンボール フィギュア | Used: ¥1,200 | List: ¥2,000 | In stock
Tool: compare_prices("フィギュア ドラゴンボール")
Results:
| # | 商品名 | 駿河屋 | まんだらけ | 楽天 | 最安 |
| 1 | ドラゴンボールZ フィギュア... | ¥3,500 | ¥3,000 | ¥3,800 | 🟢まんだらけ |
| 2 | ドラゴンボール フィギュア... | ¥1,200 | ¥2,500 | ¥1,500 | 🟢駿河屋 |
Use Cases
- AI price research agent — Ask "What's the cheapest ポケモン card across Mandarake, Suruga-ya, and Rakuten right now?"
- Resale opportunity detection — "Find items where one marketplace is 30% cheaper than the others"
- Collectibles portfolio tracking — "Check current prices for my collection across all three marketplaces"
- Best price finder — Search all three platforms with one command and see a unified comparison table
- Automated alerts — Schedule regular runs and send results to Slack/Discord via Apify webhooks
Integrations
This server runs on Apify. All underlying actors support Apify MCP Connectors (Slack, Notion, Supabase, GitHub) — connect directly from the actor's run screen.
Pricing
- $0.001 per tool call (search_mandarake_auction, search_surugaya, compare_prices)
- $0.001 per actor start (one fee per session)
- $0.00001 per result item (dataset storage fee)
- Typical single query: $0.001–$0.002 total
FAQ
What MCP transport is supported? Streamable HTTP (/mcp) and SSE (/sse).
Is this free to try? Yes — Apify provides free platform credits for new users. A few test queries cost pennies.
Can I use both tools in one conversation? Yes. The server exposes all tools simultaneously; your AI agent picks the right one.
Do I need an API key? No. Just point your MCP client at the endpoint URL.
Changelog
- v0.1.8 (2026-07-29): Reduced pricing — $0.001 per tool call. Updated README.
- v0.1.7 (2026-07-29): PPE pricing configured
- v0.1.0 (2026-07-27): Initial release with Mandarake and Suruga-ya search tools
Data & Store
- Apify Store: https://apify.com/fruitful_quintessence
- Gumroad datasets: https://atushi5.gumroad.com/l/kutuxe
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.