A11y Probe MCP server
io.github.MartinSwiss/a11y-probe-mcpMartinSwissstreamable-httpv0.1.0Scanned
Paid WCAG scans for AI agents over MCP, settled with x402 USDC on Base.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- No findings
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the A11y Probe MCP server can do
The A11y Probe MCP server is published by the GitHub account MartinSwiss. It has 4 tools. It can create or change data (3 tools: scan_page, scan_site and report), but cannot delete data. 1 tool only reads.
1 tool can send data out of your system (scan_page).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 21, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 3Claude Code: ask
reportA template Markdown accessibility report in de, fr, or en, with a prioritised fix list.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it A template Markdown accessibility report in de, fr, or en, with a prioritised fix list. Not legal advice and no compliance guarantee. No model calls. Price 1.00 USD in USDC on Base, settled after a successful scan.
Annotations the server declares
- readOnlyHint: true
scan_pageOne public page checked for WCAG issues.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it One public page checked for WCAG issues. authorized is true. No login, cookies, or stored page content. Price 0.05 USD in USDC on Base, settled after a successful scan. Automated checks find roughly 57% of WCAG issues.
Annotations the server declares
- readOnlyHint: true
scan_siteUp to 10 same-origin pages, starting from start_url.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Up to 10 same-origin pages, starting from start_url. authorized is true. Price 0.50 USD in USDC on Base, settled after a successful scan. Automated checks find roughly 57% of WCAG issues.
Annotations the server declares
- readOnlyHint: true
Only reads 1Show 1 read-only tool
get_pricingPrices in USD, rate and daily limits, and links to the terms and privacy notice.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Prices in USD, rate and daily limits, and links to the terms and privacy notice. Automated checks find roughly 57% of WCAG issues. Free.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http a11y-probe https://a11y.aiagentpay.cloud/mcpclaude mcp add --transport http a11y-probe https://a11y.aiagentpay.cloud/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__a11y-probe__get_pricing"
],
"ask": [
"mcp__a11y-probe__scan_page",
"mcp__a11y-probe__scan_site",
"mcp__a11y-probe__report"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as a11y-probe. Review it before you use it.
Capability tags behind 1 rule
- mcp__a11y-probe__scan_page outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.MartinSwiss/a11y-probe-mcp/verify?hash=348cd3acf2f95857da062494120862477349497d4978f6bb50fb3d2d5ce0838d" | jq -e '.changed == false'Pinned hash 348cd3acf2f9, from Nov 21, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.MartinSwiss/a11y-probe-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.MartinSwiss/a11y-probe-mcp)Source: MCP Registry · repository. Synced Nov 21, 2026, 21:17 UTC.
A11y Probe MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the A11y Probe MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the A11y Probe MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the A11y Probe MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the A11y Probe MCP server have?
- 4 tools: 3 write, 1 read. scan_page, scan_site, report and get_pricing.
Does the A11y Probe MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): scan_page.
Has the A11y Probe MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.