mcpbeat

Ebay Search

gooseworks-ai/ebay-search

Search eBay listings - find items, auctions, deals, and compare prices

1k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1086
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/gooseworks-ai/goose-skills --skill ebay-search

What comes with it

277 bytes besides the instruction
skill.meta.json

The instruction itself

10 sections, as written by the author

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Search eBay for products, auctions, and deals.

When to Use

  • User wants to find items on eBay
  • User asks about auctions
  • User wants to compare prices on eBay
  • User looking for used or vintage items

How It Works

Uses the SearchAPI eBay Search engine to query eBay listings.

Usage

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"ebay_search","q":"vintage watch"}}'

<details>

<summary>curl equivalent</summary>

curl -X POST "https://api.orth.sh/v1/run" \

  -H "Content-Type: application/json" \
  -d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"ebay_search","q":"vintage watch"}}'

</details>

Parameters

  • engine (required) - Must be ebay_search
  • q (required) - Search query
  • page - Page number for pagination

Response

Top-level keys: search_metadata, search_parameters, search_information, categories, organic_results, related_searches, pagination.

search_information: total_results (integer), query_displayed, sorted_by.

Each item in organic_results array:

  • position (integer) - Result rank
  • item_id (string) - eBay item ID
  • title (string) - Listing title
  • link (string) - Listing page URL
  • condition (string) - "Brand New", "Pre-Owned", "Refurbished", etc.
  • price (string) - Display price (e.g., "$199.99")
  • extracted_price (number) - Numeric price for comparison
  • original_price / extracted_original_price - Pre-discount price (if discounted)
  • shipping (string) - Shipping cost text (e.g., "Free delivery")
  • extracted_shipping (number) - Numeric shipping cost
  • buying_format (string) - "Buy It Now", "or Best Offer", or bid info with time left
  • rating (number) - Seller rating (if available)
  • reviews (integer) - Review count (if available)
  • extensions (array) - Tags like brand, material, location, "Free returns", "Last one"
  • thumbnail (string) - Image URL
  • tag (string) - Special badges like "NEW LOW PRICE" (if applicable)

Pagination: Use page=2, page=3, etc. for more results. Response includes pagination.next URL.

Examples

User: "Find vintage watches on eBay"

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"ebay_search","q":"vintage watch"}}'

User: "Search eBay for retro gaming consoles"

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"ebay_search","q":"retro gaming console"}}'

User: "Find rare vinyl records"

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"searchapi","path":"/api/v1/search","query":{"engine":"ebay_search","q":"rare vinyl records"}}'

Error Handling

  • 400 - Invalid engine name or missing q parameter
  • 401 - Invalid API key
  • 429 - Rate limit — wait and retry
  • Empty organic_results means no listings found — try broader terms
  • Use separate -q flags if & in query string causes issues: -q 'engine=ebay_search' -q 'q=vintage watch'

How to use it

Copy the folder

Take gooseworks-ai/ebay-search from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npx. Without those the skill loads but fails at the first command.