Skip to content
BuyRecord logo

BuyRecord MCP server

Which MCP servers are BuyRecord'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 2026-10-27

← Back to BuyRecord

Whose server it is
  • Registry nameapp.buyrecord/buyrecordverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools5
  • Server calls itselfBuyRecord
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 158 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Check a product's kept-or-returned rate before buying; Log whether a bought item was kept or returned.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "Check a product's kept-or-returned rate before buying", the likely first call is get_product_outcomes.
  • For "Log whether a bought item was kept or returned", the likely first call is submit_outcome.
  • 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.

Measured dailydaily checks: 2, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer509 ms
  • Space in an agent's context≈ 1,303 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results5 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 · Check a product's kept-or-returned rate before buying
  • can do · Log whether a bought item was kept or returned
  • not sure · Send order records from a shop store to buyrecord

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 →

Tools it offers5 tools · read 2026-10-27
  • search_products

    Products matching a name, GTIN or SKU: verified outcome summary, plus price, availability, rating and return policy as published on the merchant's site (labelled not verified).

  • get_product_outcomes

    Score, sample size, outcome breakdown and top return reasons for one product.

  • compare_products

    Outcomes for 2 to 5 products, in the order given.

  • get_merchant_profile

    Return rate, complaint rate and delivery issue rate across a merchant's products.

  • submit_outcome

    Record a purchase outcome for a product (product_id or product_url). Requires an API key (Authorization: Bearer header). Proofs: shopify_order (shop domain, order number, confirmation number) is checked against the shop's order record…

How to connect

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

{
  "mcpServers": {
    "buyrecord": {
      "type": "http",
      "url": "https://api.buyrecord.app/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http buyrecord https://api.buyrecord.app/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

9 paths, read 2026-10-27. 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.