
국내외 AI 상품 인덱스 MCP server
Which MCP servers are 국내외 AI 상품 인덱스's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namecom.hadacart/catalog-snapshotsverified in the MCP registry
The registry name sits under hadacart.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools4
- Server calls itselfcom.hadacart/catalog-snapshots
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 189 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "search Korean and US merchant products by keyword", the likely first call is search_products.
- Parameters are untyped or undescribed in 5 of 5 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score94 of 100answers 100 · definitions 83 · context 93 · connects 100
- Answered100% of days7 of 7 daily checks
- Median first answer627 ms
- Space in an agent's context≈ 3,924 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 5 of 5
What an agent can do with it
- can do · search Korean and US merchant products by keyword
- not sure · compare option prices in KRW and USD
- not sure · retrieve product data as JSON or markdown
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
find_buying_guidesDiscover KR/US buying questions, dated comparison evidence and exact product routes. Find validated reviewed-question text as documentation, with exact FAQ citations. Questions may ask about unsupported claims; answer/exclusion prose is…
find_purchase_candidatesFind products with original issued affiliate purchase links for the actual buyer country, currency, quantity and options. Compare dated pack unit prices; use responseMode brief. Zero candidates include noMatchGuidance.catalogCoverage…
search_productsSearch multiple KR/US merchant catalogs by product keywords or exact identifiers; use affiliateLinkedOnly true to find recorded issued purchase routes. Whole-query exact recorded ISBN13 (optional ISBN prefix), catalog product ID, SKU or…
get_productRead one exact product with dated options, native prices, source evidence and original merchant purchase route. recordedBenefitRestrictions contains dated exact-product purchase exclusions, separate from affiliate commission rules; never…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"catalog-snapshots": {
"type": "http",
"url": "https://hadacart.com/api/catalog/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http hadacart https://hadacart.com/api/catalog/mcpclaude.ai, ChatGPT and other clients: add https://hadacart.com/api/catalog/mcp as a custom connector in the settings.
OpenAPI spec
24 paths, read 2026-10-28. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.