Skip to content
Iron/Out logo

Iron/Out MCP server

Which MCP servers are Iron/Out'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 2026-11-02

← Back to Iron/Out

Whose server it is
  • Registry nameio.iron-out/ux-benchmarkverified in the MCP registry

The registry name sits under iron-out.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-02
  • Stateanswerschecked 2026-11-02
  • Tools2
  • Server calls itselfiron-out-ux-score
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 357 ms.

Should an agent connect itNot proven either way yet
  • Its tools do measure real user performance on live pages, but not prioritise performance fixes by revenue impact; fix core web vitals failures on checkout and product pages.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "measure real user performance on live pages", the likely first call is run_ux_benchmark.

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: 3, the first on 2026-11-02
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it1 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer469 ms
  • Space in an agent's context≈ 516 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · measure real user performance on live pages
  • cannot · prioritise performance fixes by revenue impact
  • cannot · fix core web vitals failures on checkout and product pages

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 offers2 tools · read 2026-11-02
  • run_ux_benchmark

    Returns the Iron/Out UX Score (0 to 100) for one website, using real-user Chrome UX Report (CrUX) data from the last 28 days. The score is built on five Web Vitals: TTFB (10%), FCP (15%), LCP (25%), INP (25%) and CLS (25%). Use this when…

  • compare_sites

    Compares the Iron/Out UX Score of 2 to 5 websites side by side, using real-user Chrome UX Report (CrUX) data from the last 28 days (Web Vitals: TTFB, FCP, LCP, INP, CLS). Use this for competitor or sector comparisons. It runs no lab test…

How to connect

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

{
  "mcpServers": {
    "ux-benchmark": {
      "type": "http",
      "url": "https://www.iron-out.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http iron-out https://www.iron-out.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.iron-out.io/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.