Japan Market Data › Japan Market Data MCP Server
An assistant asked about current Japanese prices will answer from training data, which means it is wrong the moment a rerun hits or a seller cuts a price. The fix is to give the agent a tool that returns live listings instead of a recollection.
Several of these scrapers are exposed as MCP servers, so a compatible client — Claude Desktop, Cursor, or your own harness — can call them directly. The agent requests a search, receives JSON records, and reasons over current data.
item_name | Product title returned to the agent. |
|---|---|
current_price_jpy | Live price the agent quotes, with the run timestamp as context. |
condition | Lets the agent distinguish sealed from opened stock. |
item_url | Citation URL so a human can verify the agent's claim. |
Field names follow the actor's dataset schema and can differ slightly between actors — check the actor page for the exact input and output schema before wiring it into a pipeline.
Starting a run: pick the actor for your marketplace from the publisher page, then start it from the Apify console or the API. Billing is per result returned (roughly $0.002 per item), so a scoped search stays cheap.
curl "https://api.apify.com/v2/datasets/$DATASET_ID/items?token=$APIFY_TOKEN&format=json"