About scandiary
scandiary is a CLI and MCP server that checks websites for axe-core accessibility issues and produces a fix prompt for coding tools. It runs checks using a local browser and can scan a supplied URL, including localhost.
Key features
- 01Scan websites with axe-core
- 02Check WCAG 2.0 and 2.1 A/AA
- 03Generate prompts with issue examples
- 04Output JSON or prompt-only results
- 05Strict mode for CI
Use cases
- 01Find accessibility issues on a local site
- 02Prepare a fix prompt for a coding tool
- 03Run accessibility checks in CI
- 04Ask an MCP client to scan a URL
MCP support
Runs over stdio as an MCP server and exposes the check_accessibility tool, which accepts a URL and optional page count and returns a fix prompt.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
1Saved tool list · updated 4d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | Site to check, for example https://example.com or localhost:3000 |
| pages | integer | No | Pages to check (default 5) |
Details
From the project READMEscandiary
Check the accessibility of a site you built with Claude Code, Cursor, Lovable or by hand, then paste the result into your AI tool as a fix prompt.
npx scandiary https://your-site.com
npx scandiary localhost:3000
No signup and no API key. It uses the Chrome, Edge or Brave already on your machine.
Get a fix prompt
npx scandiary https://your-site.com --prompt > fix-a11y.md
Paste that file into your coding tool. Each issue comes with real examples from your pages and a note on how to fix it properly. The prompt also tells your tool what not to do: no overlay scripts, no hiding elements just to pass, and no saying the work is done until a new scan confirms it.
Use it from Claude Code
Install the skill once:
mkdir -p ~/.claude/skills/scandiary
curl -o ~/.claude/skills/scandiary/SKILL.md https://raw.githubusercontent.com/Yedigarli/scandiary-cli/master/skills/scandiary/SKILL.md
Then ask in plain words, for example "check the accessibility of localhost:3000 and fix what you find". Claude runs the check, edits your code, and runs the check again before it reports the numbers. It lists any labels it had to guess so you can review them.
Use it as an MCP server
For Cursor, Claude Desktop, Windsurf or any MCP client, add this to the client's MCP config:
{
"mcpServers": {
"scandiary": {
"command": "npx",
"args": ["-y", "scandiary", "--mcp"]
}
}
}
It adds one tool, check_accessibility, which takes a url and an optional pages count and returns the fix prompt. In Claude Code: claude mcp add scandiary -- npx -y scandiary --mcp.
Options
| Option | What it does |
|---|---|
--pages <n> | Pages to check. Default 5, max 100 |
--prompt | Print only the fix prompt |
--json | Print the full result as JSON |
--strict | Exit with code 1 when issues are found, for CI |
--mcp | Run as an MCP server over stdio |
Exit codes: 0 finished, 1 issues found with --strict, 2 the check could not run.
What this can and cannot tell you
Automated checks find roughly a third of accessibility problems, this one included. The rest needs a person using a keyboard and a screen reader.
A short list, or an empty one, does not mean your site is accessible. It does not say whether you meet any legal standard.
Rules come from axe-core: WCAG 2.0 and 2.1, levels A and AA.
Page content in the prompt is treated as untrusted data. It is flattened, shortened and marked so your AI tool should not follow anything written inside it. Review what your tool changes, as you would with any generated code.
Privacy
The check runs on your machine. This tool sends no telemetry and has no analytics. Your browser opens the pages you asked it to check, along with whatever those pages load, as in a normal visit.
Weekly checks
A one-off scan tells you where you stand today. Scandiary runs the check every week and emails what changed, so you keep a dated history. The free plan covers 25 pages.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.