RatedWithAI MCP

A remote MCP server that allows AI assistants to scan live web pages for WCAG 2.1/2.2 AA accessibility issues using axe-core. It returns a 0-100 score, letter grade, failing rules, and example elements. It supports scanning up to three pages per request and provides explanations for accessibility issues. The server is read-only and refuses to scan private networks or login-protected pages.

Visit RatedWithAI

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by RatedWithAI

MCP endpoint (Streamable HTTP)

https://ratedwithai.com/api/mcp

Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

2 of 2 have a description · 2 of 2 declare behavior hints · 2 of 2 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 8:17 PM UTC
Passed Official MCP Registry namespace is tied to ratedwithai.com · Nov 6, 2026, 7:53 PM UTC
Passed Endpoint is on the registry namespace domain · Nov 6, 2026, 7:53 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Scan a public web page for WCAG 2.1/2.2 AA accessibility issues
Explain specific axe-core rule failures and how to fix them
Get a 0-100 accessibility score and letter grade for a site
Check accessibility of up to three pages on the same domain

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: com.ratedwithai/accessibility-checker@1.0.0 Project website

Protocol and capabilities

Server: ratedwithai 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

ratedwithai runs a real WCAG 2.1/2.2 accessibility scan (axe-core in a headless browser) against a live public web page and reports the failing rules, how many elements each one affects, and example markup. Use scan_accessibility when the user wants a website or URL checked for accessibility, ADA/WCAG/EAA compliance problems, screen-reader or keyboard barriers, or an accessibility score. Use explain_accessibility_issue when the user asks how to fix a specific axe rule id returned by a scan (for example color-contrast or image-alt). Do not use these tools for questions about accessibility law in general, for pages behind a login, or for local files and HTML snippets — the scanner only loads public http(s) URLs. A scan is automated: it catches roughly a third to a half of WCAG issues and is not a legal compliance certification; say so when presenting results.

Tools

2 advertised

scan_accessibility — Scan a website for accessibility issues

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

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 0-100 score, a letter grade and the failing rules with example elements. Takes 15-40 seconds. Do not use it for pages that need a login, for localhost or private-network addresses, or for pasted HTML.

scan_accessibility input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Public website address, e.g. example.com or https://example.com/about"
    }
  },
  "additionalProperties": false
}

scan_accessibility output schema

{
  "type": "object",
  "required": [
    "url",
    "score",
    "grade",
    "pagesScanned",
    "failingRuleCount",
    "affectedElementCount",
    "needsReviewCount",
    "rulesOmitted",
    "violations",
    "scannedAt",
    "moreInfoUrl"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL that was scanned, after normalisation."
    },
    "grade": {
      "enum": [
        "A",
        "B",
        "C",
        "D",
        "F"
      ],
      "type": "string"
    },
    "score": {
      "type": "number",
      "description": "0-100, weighted by violation severity."
    },
    "scannedAt": {
      "type": "string"
    },
    "violations": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "ruleId",
          "impact",
          "summary",
          "wcag",
          "elementCount",
          "examples"
        ],
        "properties": {
          "wcag": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "impact": {
            "type": "string"
          },
          "ruleId": {
            "type": "string"
          },
          "summary": {
            "type": "string"
          },
          "examples": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "selector",
                "html"
              ],
              "properties": {
                "html": {
                  "type": "string"
                },
                "selector": {
                  "type": "string"
                }
              }
            }
          },
          "elementCount": {
            "type": "integer"
          }
        }
      }
    },
    "moreInfoUrl": {
      "type": "string",
      "description": "Informational page on scheduled re-scans and fix help for this kind of result."
    },
    "pagesScanned": {
      "type": "integer"
    },
    "rulesOmitted": {
      "type": "integer",
      "description": "Failing rules not listed because the response is capped."
    },
    "failingRuleCount": {
      "type": "integer"
    },
    "needsReviewCount": {
      "type": "integer",
      "description": "Checks axe could not decide automatically; a human must confirm them."
    },
    "affectedElementCount": {
      "type": "integer"
    }
  }
}

scan_accessibility annotations

{
  "title": "Scan a website for accessibility issues",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

explain_accessibility_issue — Explain how to fix an accessibility rule

Advertised by the server during the last successful anonymous check.

Advertised read-only

Use this when the user asks what an axe-core accessibility rule means or how to fix it — such as color-contrast, image-alt, label or link-name. Returns plain-English steps and a code example. Do not use it when the user wants a site checked; it explains a rule and does not scan pages.

explain_accessibility_issue input schema

{
  "type": "object",
  "required": [
    "rule_id"
  ],
  "properties": {
    "rule_id": {
      "type": "string",
      "description": "axe-core rule id, e.g. color-contrast"
    }
  },
  "additionalProperties": false
}

explain_accessibility_issue output schema

{
  "type": "object",
  "required": [
    "ruleId",
    "known",
    "summary",
    "steps",
    "referenceUrl"
  ],
  "properties": {
    "known": {
      "type": "boolean"
    },
    "steps": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "ruleId": {
      "type": "string"
    },
    "summary": {
      "type": "string"
    },
    "codeExample": {
      "type": "string"
    },
    "referenceUrl": {
      "type": "string"
    }
  }
}

explain_accessibility_issue annotations

{
  "title": "Explain how to fix an accessibility rule",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 710 ms
95th percentile latency: 710 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 8:17 PM UTC · probe · passed · 710 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add ratedwithai-mcp --url https://ratedwithai.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ratedwithai-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "ratedwithai-mcp": {
      "url": "https://ratedwithai.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "ratedwithai-mcp": {
      "type": "streamableHttp",
      "url": "https://ratedwithai.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ratedwithai-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://ratedwithai.com/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "ratedwithai-mcp": {
      "serverUrl": "https://ratedwithai.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like RatedWithAI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 8,317

Do you run RatedWithAI MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing