About Japan Price Alert MCP
Japan Price Alert MCP is a price-monitoring server for AI agents tracking products on major Japanese e-commerce sites. It manages watches, price history and alerts through several notification channels.
Key features
- 01Monitor prices across six Japanese platforms
- 02Create and manage product watches
- 03Check prices on demand or in batches
- 04Retrieve price history
- 05Alert on price, stock or percentage changes
- 06Send notifications by log, Telegram or webhook
Use cases
- 01Track a product until it reaches a target price
- 02Review price history before buying
- 03Receive alerts when an item is back in stock
MCP support
It exposes price-watch management, platform detection and price-history tools to MCP clients. Notifications can be sent through log, Telegram or webhook channels.
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 READMEjapan-price-alert-mcp
Japanese EC price-change monitoring and notification MCP server for AI agents.
Overview
Monitor product prices across major Japanese e-commerce platforms (Mercari, Yahoo Auctions, Rakuten, SUUMO, Kakaku.com) and receive instant alerts on price drops.
Built on the Kensho project's price monitoring engine.
Platforms
- Mercari Japan (メルカリ) - jp.mercari.com
- Yahoo! Auctions / Shopping (ヤフオク) - auctions.yahoo.co.jp, shopping.yahoo.co.jp
- Rakuten Ichiba (楽天市場) - item.rakuten.co.jp
- SUUMO (SUUMO) - suumo.jp
- Kakaku.com (価格.com) - kakaku.com
- Suruga-ya (駿河屋) - suruga-ya.jp
Tools
| Tool | Description |
|---|---|
create_price_watch | Register a new product URL for price monitoring |
list_price_watches | List all registered watches |
get_price_watch | Get details of a specific watch |
update_price_watch | Update watch parameters (target price, interval, etc.) |
delete_price_watch | Remove a watch |
check_price_watch | Force immediate price check |
run_due_price_checks | Batch check all due watches |
get_price_history | Get historical price data |
detect_platform_url | Detect platform from URL |
Installation
Smithery (Recommended)
npx @smithery/cli install atushi1841/japan_price_alert_mcp
Manual
# Clone or extract the MCPB bundle
# Configure in your MCP client:
{
"servers": {
"japan-price-alert-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/bundle", "src/stdio_main.py"]
}
}
}
Configuration
| Environment Variable | Description | Default |
|---|---|---|
PRICE_WATCH_DB | Custom SQLite database path | <bundle>/data/price_watch.db |
TELEGRAM_BOT_TOKEN | Telegram bot token (for notifications) | - |
TELEGRAM_CHAT_ID | Telegram chat ID (for notifications) | - |
Usage Examples
// Create a price watch
const result = await mcp.callTool("create_price_watch", {
user_id: "user123",
url: "https://www.mercari.com/us/item/m123456789/",
target_price_jpy: 5000,
notification_channel: "telegram",
notification_destination: "123456789",
check_interval_minutes: 30
});
// Check a specific watch
const check = await mcp.callTool("check_price_watch", {
watch_id: "pw_abc123"
});
// List all watches
const list = await mcp.callTool("list_price_watches", {
user_id: "user123"
});
Alert Conditions
- lte (default): Alert when price <= target_price_jpy
- any_drop: Alert on any price decrease
- percent_drop: Alert when price drops by >= drop_percentage%
- in_stock: Alert when item comes back in stock
Notification Channels
- log (default): Log to stderr
- telegram: Send to Telegram bot (requires token + chat_id)
- webhook: POST to specified URL
- email: Log email alert (SMTP not implemented)
Dependencies
- Python >=3.10
- fastmcp >=3.0.0
- stdlib only for scraping (no external dependencies beyond fastmcp)
License
MIT
Author
atushi1841
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.