Skip to content

Measured Size MCP server

Which MCP servers are Measured Size'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 Measured Size

Whose server it is
  • Registry namecom.measuredsize/fitverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools4
  • Server calls itselfcom.measuredsize/fit
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 129 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.

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
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer91 ms
  • Space in an agent's context≈ 962 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 offers4 tools · read 2026-10-27
  • bra_size_from_measurements

    Her bra size from her underbust and bust measurements (inches or cm, decimals allowed): her base US size, sister sizes one band each way, the UK size, EU and French sizes where their tables give the whole size, and the usual letter size…

  • bra_size_at_brand

    Her size at one brand, in that brand's own labels (for example 32E at a UK-lettered brand where her US size is 32DDD), for its band and cup bras and for its letter-sized styles, each with a confidence badge and a reason. Use this when a…

  • translate_bra_size

    Translate a band and cup size she wears at one brand (for example 34DD at Wacoal) into another brand's label, through Measured Size's base size. Use this only when the shopper has no measurements; measurements give a better answer…

  • list_bra_brands

    The brands Measured Size has researched, with their other names, whether they sell band and cup sizes or letter sizes, their cup letters, band and cup ranges, whether their own letter chart is on file, and when their record was last…

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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

OpenAPI spec

4 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.