Skip to content

BRAINIAC Accessibility Intelligence MCP server

software.brainiac/accessibilitybrainiac.softwarestreamable-httpv1.0.1Scanned

Paid Accessibility Intelligence API via x402. Unpaid tool calls return 402.

10 tools: 8 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 8 write, 2 read.
  • Reads private data · 1
  • Reads text others write · 10
  • Can send data out · 10
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

8 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.
Govern this server →

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 BRAINIAC Accessibility Intelligence MCP server can do

The BRAINIAC Accessibility Intelligence MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 10 tools. It can create or change data (8 tools: accessibility_html-audit, accessibility_image-alt-text-audit, accessibility_form-audit, accessibility_link-audit and 4 more), but cannot delete data. 2 tools only read.

1 tool reads private data (accessibility_document-language-check); 10 tools bring in text other people can write (accessibility_html-audit, accessibility_image-alt-text-audit, accessibility_heading-structure-audit and 7 more); 10 tools can send data out of your system (accessibility_html-audit, accessibility_image-alt-text-audit, accessibility_heading-structure-audit and 7 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.0.1.

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.

10 tools

Changes things 8Claude Code: ask
  • accessibility_aria-attribute-auditCheck roles, boolean ARIA values, and references to ids that exist in this HTML.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Check roles, boolean ARIA values, and references to ids that exist in this HTML. Runtime ARIA state changes are not tested. Price $0.04 USDC. POST /api/v1/accessibility/aria-attribute-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit ARIA attributes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_color-contrast-checkCalculate a contrast ratio only when both colours are opaque values on the same element.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Calculate a contrast ratio only when both colours are opaque values on the same element. A single colour is not compared with an assumed background. Price $0.04 USDC. POST /api/v1/accessibility/color-contrast-check. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Check inline colour contrast
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_form-auditCheck that controls have a label, an aria-label, or a matching label element.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Check that controls have a label, an aria-label, or a matching label element. A placeholder or title is not treated as a sufficient name. Price $0.04 USDC. POST /api/v1/accessibility/form-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit form accessibility
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_html-auditRun the static image, heading, form, link, language, keyboard, ARIA, and inline-contrast checks.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Warn

      The server marks "accessibility_html-audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Run the static image, heading, form, link, language, keyboard, ARIA, and inline-contrast checks. The result is not a WCAG conformance claim. Price $0.05 USDC. POST /api/v1/accessibility/html-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit HTML accessibility
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_image-alt-text-auditFlag images, image inputs, and areas with no alt attribute.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Flag images, image inputs, and areas with no alt attribute. An empty alt is reported as a manual check, not as a confirmed failure. Price $0.03 USDC. POST /api/v1/accessibility/image-alt-text-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit image alt text
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_keyboard-signalsFlag a positive tabindex and an onclick on a non-control.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Flag a positive tabindex and an onclick on a non-control. Keys are not pressed, so keyboard operation stays a manual check. Price $0.04 USDC. POST /api/v1/accessibility/keyboard-signals. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Check keyboard signals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_remediation-reportCombine the static checks and list confirmed issues before potential issues and manual checks.Reads text others writeCan 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Combine the static checks and list confirmed issues before potential issues and manual checks. The report does not claim WCAG conformance. Price $0.12 USDC. POST /api/v1/accessibility/remediation-report. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Report accessibility remediation
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • accessibility_document-language-checkRead the lang attribute on the html element.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe name "accessibility_document-language-check" says "document": it reads documents.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "read" and "html": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read the lang attribute on the html element. The page text is not compared with that value, and a fragment without html is not marked as a failure. Price $0.02 USDC. POST /api/v1/accessibility/document-language-check. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Check document language
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • accessibility_heading-structure-auditRead heading elements in source order and flag empty headings and skipped levels.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read heading elements in source order and flag empty headings and skipped levels. A missing h1 is a potential issue, not a confirmed failure. Price $0.03 USDC. POST /api/v1/accessibility/heading-structure-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit heading structure
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: 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.

100 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__accessibility__accessibility_document-language-check"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:20 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.brainiac.software/mcp/accessibility: tools/list returned 10 tools to an anonymous client, including accessibility_html-audit (write), accessibility_image-alt-text-audit (write), accessibility_form-audit (write), accessibility_link-audit (write), accessibility_keyboard-signals (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "accessibility_html-audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

    What this check looks for
  • The server marks "accessibility_link-audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "accessibility_link-audit" says "link": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools10 changed.~10 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http accessibility https://www.brainiac.software/mcp/accessibility
claude mcp add --transport http accessibility https://www.brainiac.software/mcp/accessibility

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__accessibility__accessibility_html-audit",
      "mcp__accessibility__accessibility_image-alt-text-audit",
      "mcp__accessibility__accessibility_heading-structure-audit",
      "mcp__accessibility__accessibility_form-audit",
      "mcp__accessibility__accessibility_link-audit",
      "mcp__accessibility__accessibility_document-language-check",
      "mcp__accessibility__accessibility_keyboard-signals",
      "mcp__accessibility__accessibility_aria-attribute-audit",
      "mcp__accessibility__accessibility_color-contrast-check",
      "mcp__accessibility__accessibility_remediation-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 accessibility. Review it before you use it.

Capability tags behind 10 rules
  • mcp__accessibility__accessibility_html-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_image-alt-text-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_heading-structure-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_form-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_link-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_document-language-check private-data, untrusted-input, outbound
  • mcp__accessibility__accessibility_keyboard-signals untrusted-input, outbound
  • mcp__accessibility__accessibility_aria-attribute-audit untrusted-input, outbound
  • mcp__accessibility__accessibility_color-contrast-check untrusted-input, outbound
  • mcp__accessibility__accessibility_remediation-report untrusted-input, 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/software.brainiac/accessibility/verify?hash=d4a16770a27a5f8c29a8a79927fef46e1fc83c2b189a557db5dfad61cad0aba6" | jq -e '.changed == false'

Pinned hash d4a16770a27a, from Nov 20, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/software.brainiac/accessibility/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for software.brainiac/accessibility
[![Anlyon Radar](https://radar.anlyon.com/badge/software.brainiac/accessibility.svg)](https://radar.anlyon.com/servers/software.brainiac/accessibility)

Source: MCP Registry. Synced Nov 20, 2026, 01:17 UTC.

BRAINIAC Accessibility Intelligence MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BRAINIAC Accessibility Intelligence MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 8 of which can change, send or delete something, and 2 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 BRAINIAC Accessibility Intelligence MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BRAINIAC Accessibility Intelligence 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 BRAINIAC Accessibility Intelligence MCP server have?

10 tools: 8 write, 2 read. accessibility_html-audit, accessibility_image-alt-text-audit, accessibility_form-audit, accessibility_link-audit, accessibility_keyboard-signals, accessibility_aria-attribute-audit, accessibility_color-contrast-check, accessibility_remediation-report and 2 more.

Does the BRAINIAC Accessibility Intelligence MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BRAINIAC Accessibility Intelligence MCP server send data to outside services?

10 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): accessibility_html-audit, accessibility_image-alt-text-audit, accessibility_heading-structure-audit, accessibility_form-audit, accessibility_link-audit, accessibility_document-language-check and 4 more.

Has the BRAINIAC Accessibility Intelligence MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.