linkfox-ehunt-temu-product-query

EHunt Temu product query (ehunt/temu/productQuery）

When the LinkFox "Third-Party Data Service" MCP is available, the corresponding gateway route ehunt/temu/productQuery is called (MCP display name:Temu product query, the exact tool name is subject to the tool metadata issued in the current environment). Authentication and upstream routing are handled by the gateway; if the response contains a root-level code field, whether it succeeds is subject to the live network.

Key points

• Pagination：page starts from 1;pageSize defaults to 20, maximum 100 (recommended ≤50).
• Range input parameters：*Begin / *End appear in pairs (price, rating, reviews, total/weekly/daily sales, listing time) to form the upstream range.
• Category：categoryHome frontend category ID,categoryBackend backend category ID; you can first use Temu category search to get the id.
• Managed mode：isLocal(0=fully managed, 1=semi-managed); for semi-managed you can use region to limit the region (multiple separated by commas).
• Listing/delisting：soldOut(0=listed, 1=delisted).
• Tags：tags / customTags multiple separated by commas.
• Sorting：sortBy is a "field-direction" string, such as order_week-0(weekly sales descending, default),price-0、order_total-0、rating-0。

Script (optional)

Command-line debugging:python scripts/ehunt_temu_product_query.py '<JSON>'(requires LINKFOXAGENT_API_KEY). See the end of references/api.md .

Reference

For the input/output parameter table, see references/api.md。

Handling Large Responses

To avoid overflowing the agent context, persist the response to disk and extract only the fields you need:

python scripts/response_io.py run --script scripts/ehunt_temu_product_query.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>"   # or --path "<JMESPath>"

Pick --out-dir outside any git working tree (e.g. /tmp/... on Unix, %TEMP%/... on Windows). Persisted responses may contain PII, pricing, or auth-sensitive data — do not commit them. Files are not auto-deleted; clean up when the task is done.

run writes the full response to a file and emits only a schema preview + file path. read projects specific fields, with --limit/--offset for slicing and --format json|jsonl|csv|table for output.

When to prefer this pattern — apply your judgment based on the response characteristics, e.g.:

• High field count per record, or fields you don't need
• Batch/paginated results (multiple items per call)
• Long-text fields (descriptions, reviews, HTML, time series)
• Output reused across later steps rather than consumed immediately

For small, single-use responses, calling the main script directly is fine.

⚠️ The preview is a truncated schema + sample, not the full data. Any field-level decision must read from the persisted file via read.