Skip to content
Kaupia logo

Kaupia MCP server

Which MCP servers are Kaupia'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 2026-10-31

← Back to Kaupia

Whose server it is
  • Registry namecom.kaupia/kaupiaverified in the MCP registry

The registry name sits under kaupia.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-31
  • Stateanswerschecked 2026-10-31
  • Tools5
  • Server calls itselfkaupia
  • Server version1.27.0
  • Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 697 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: search, compare and buy products through one MCP endpoint; keep a store's own checkout while receiving agent orders.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • For "search, compare and buy products through one MCP endpoint", the likely first call is search_products.
  • create_checkout change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 7 of 8 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.

Measured dailydaily checks: 4, the first on 2026-10-31
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer140 ms
  • Space in an agent's context≈ 1,000 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsC · 69 of 100
  • Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 8
  • Not saying whether it only reads or can destroy: 8 of 8

What an agent can do with it

  • can do · search, compare and buy products through one MCP endpoint
  • not sure · list a store so AI agents can place orders
  • can do · keep a store's own checkout while receiving agent orders

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

  • Tools that change data, on a server that answers without a sign-in: create_checkout

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 →

Tools it offers5 tools · read 2026-10-31
  • search_products

    Search products for a buyer intent. Returns ranked candidates with price, availability and product_id. Call get_product(product_id) before quoting a specific variant. Prices in major units (USD).

  • get_product

    Live details for one product: variants, price, stock status, checkout links.

  • create_checkout

    Start a purchase. v0 returns the merchant's checkout link for the chosen variant plus a Kaupia checkout_id. Keep the checkout_id and call report_outcome later so the order is covered and ranked.

  • report_outcome

    Report what happened to a checkout: placed | delivered | wrong_item | late | refunded | failed.

  • shop_scorecard

    Per-shop outcome stats collected through Kaupia (delivered vs problems).

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "kaupia": {
      "type": "http",
      "url": "https://api.kaupia.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http kaupia https://api.kaupia.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.kaupia.com/mcp as a custom connector in the settings.

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.