Skip to content
Avahit logo

Avahit MCP server

Which servers in the official MCP registry are Avahit's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to Avahit

Whose server it is
  • Registry namecom.avahit/catalogverified in the MCP registry

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

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools4
  • Server calls itselfavahit-catalog
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 478 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 2 of 4 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 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer514 ms
  • Space in an agent's context≈ 503 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 4

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 offers4 tools · read 2026-10-24
  • search_products

    Search Avahit's catalog of direct-to-consumer brand products whose prices Avahit re-checks at the store every day. Returns title, current price with the date of the last check, store domain, store rating and a link to the product page on…

  • compare_alternatives

    Given an Avahit product id, return ranked alternatives with a match percentage explaining how close each one is (same category, price distance, product type, same store).

  • get_store_sales

    When does a brand store have sales? Given a store domain or brand name (e.g. 'glossier.com', 'Boll & Branch'), return the sales it announced on its homepage or by email to newsletter subscribers with dates, whether product prices actually…

  • get_price_history

    Given an Avahit product id, return what Avahit itself observed about its price: current price and when it was last verified against the store, the lowest and highest price seen with dates, the average, how many checks and since when…

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://avahit.com/api/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.