Skip to content
buyer.sh logo

buyer.sh MCP server

Which MCP servers are buyer.sh'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 buyer.sh

Whose server it is
  • Registry namesh.buyer/searchverified in the MCP registry

The registry name sits under buyer.sh. 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
  • Tools1
  • Server calls itselfbuyer.sh
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 111 ms.

Should an agent connect itNot proven either way yet
  • Its tools do Find products matching natural-language constraints like quiet, mac-compatible, or price cap; Compare ranked product matches across marketplaces, stores and seller feeds, but not Check stock and delivery timing before an agent recommends a purchase.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "Find products matching natural-language constraints like quiet, mac-compatible, or price cap", the likely first call is search_products.
  • For "Compare ranked product matches across marketplaces, stores and seller feeds", the likely first call is search_products.

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 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer139 ms
  • Space in an agent's context≈ 187 tokensthe definitions of all its tools (1), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · Find products matching natural-language constraints like quiet, mac-compatible, or price cap
  • can do · Compare ranked product matches across marketplaces, stores and seller feeds
  • cannot · Check stock and delivery timing before an agent recommends a purchase

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 offers1 tools · read 2026-10-27
  • search_products

    Search products across online stores. Returns title, price, merchant, rating, product URL and a direct checkout URL when available.

How to connect

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

{
  "mcpServers": {
    "search": {
      "type": "http",
      "url": "https://api.buyer.sh/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http buyer https://api.buyer.sh/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.buyer.sh/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.