Skip to content
RatedWithAI logo

RatedWithAI MCP server

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

read 2026-10-18

← Back to RatedWithAI

Whose server it is
  • Registry namecom.ratedwithai/accessibility-checkerverified in the MCP registry

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

When we asked itchecked 2026-10-18
  • Stateanswerschecked 2026-10-18
  • Tools2
  • Server calls itselfratedwithai
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-18 the server answered initialize and tools/list without a sign-in. First answer in 293 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 3 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: 3, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer183 ms
  • Space in an agent's context≈ 309 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results2 of 2 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 (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 offers2 tools · read 2026-10-18
  • scan_accessibility

    Use this when the user wants a public website or web page checked for accessibility (WCAG 2.1/2.2 AA, ADA, EAA, Section 508): it loads the live page in a real browser, runs axe-core on it and up to two more same-site pages, and returns a…

  • explain_accessibility_issue

    Use this when the user asks what an axe-core accessibility rule means or how to fix it — typically a ruleId returned by scan_accessibility, such as color-contrast, image-alt, label or link-name. Returns plain-English steps and a code…

How to connect

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

{
  "mcpServers": {
    "accessibility-checker": {
      "type": "http",
      "url": "https://ratedwithai.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://ratedwithai.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.