mcpField
L
linkfox-ehunt-etsy-category-search

linkfox-ehunt-etsy-category-search

github.com/linkfox-aiData & databases113132 installsUpdated 2w ago
Repository

About linkfox-ehunt-etsy-category-search

A skill for searching Etsy categories in the local MCP library provided by LinkFox's third-party data service. The full category set must be synced first; returned category IDs can be used in product or store queries.

Key features

  1. 01Match category names, IDs, or parent IDs
  2. 02Support paginated searches
  3. 03Return category IDs for later queries

Use cases

  1. 01Find Etsy categories and their IDs
  2. 02Prepare category identifiers for product queries
  3. 03Search the local category library after syncing

MCP support

Calls `_ehunt_etsyCategorySearch` through LinkFox's third-party data service MCP to search categories previously written by `_ehunt_syncEtsyCategory`.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-ehunt-etsy-category-search

After installing, type/linkfox-ehunt-etsy-category-searchin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
api.md
scripts/
ehunt_etsy_category_search.py
response_io.py

Details

From the project README

EHunt Etsy 类目检索（_ehunt_etsyCategorySearch）

在具备 LinkFox「第三方数据服务」MCP 时，按工具名 _ehunt_etsyCategorySearch 调用（MCP 展示名：Etsy品类查询，以当前环境下发的工具元数据为准）。数据来自 MCP 库本地检索。

前置条件

库内须已有 _ehunt_syncEtsyCategory 写入的全量类目（MCP 展示名：Etsy品类同步）。若无数据或结果为空，应先完成同步再检索。

要点

  • 必填：keyword（子串匹配类目名称、类目 id、parentIds）。
  • 分页：page 从 1 起；pageSize 默认 50、最大 200。
  • 返回的 id 可作为 _ehunt_productQuery / 店铺侧 category 等入参的类目标识（与具体工具 schema 一致即可）。

脚本（可选）

命令行调试：python scripts/ehunt_etsy_category_search.py '<JSON>'（需 LINKFOXAGENT_API_KEY）。详见 references/api.md 末尾。

参考

入参/出参表见 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_etsy_category_search.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.

Comments

Markdown supported