WCAG Accessibility Audit MCP Server

Audit WCAG accessibility

audit_wcag_accessibility

Read-onlyIdempotent

Audits one or more website domains for WCAG accessibility issues in a real browser, returning failing rules by impact, affected elements, a 0–100 score, and EAA exposure signals.

Instructions

Audit websites for accessibility with axe-core in a real browser. Give one domain or a list; each domain returns one row with the WCAG issues automated checks find (distinct failing rules by impact, affected element count, top failing rules with help links, sample selectors), a 0 to 100 score, European Accessibility Act exposure signals, and optional presence checks for an accessibility statement, an accessibility overlay widget, a privacy policy, a German Impressum, and the US privacy choice link and GPC file. Blocked, timed out, or unreachable sites return a free row that says why. Automated checks find a subset of WCAG failures and the result is never a conformance claim. A run that does not succeed is returned as an error with its run ID. Read-only on the audited sites; requires an APIFY_TOKEN and consumes Apify credits per audited domain.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_wcag_accessibility"
  }
}

Input Schema

Name	Required	Description
`pages`	No	Pages per domain. 1 audits the homepage; 2 to 5 add pages from the sitemap or the homepage navigation, each charged as page-audited. Default 1.
`domain`	No	One website domain, for example mambabuilt.com. The homepage is audited. Required unless domains is set.
`domains`	No	A list of website domains, one row per domain. Used instead of domain when set.
`standard`	No	Rule set to run. ada runs WCAG 2.1 AA, the level the ADA Title II rule names. en301549 runs the rules axe maps to EN 301 549, the standard the EAA points to. Default wcag21aa.
`viewport`	No	desktop renders at 1280 by 800; mobile at 390 by 844 with touch. Default desktop.
`skipCache`	No	false reuses an identical audit from the last 24 hours; true audits fresh. Default false.
`max_charge_usd`	No	Optional cost cap in USD, for example 1.50. The run stops before starting a domain that could take its charges past it.
`compliance_checks`	No	Optional presence checks, charged once per domain as compliance-checked when any is set. impressum runs only on German language or .de sites and reports field types, never values.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 29, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover read-only, open-world, idempotent, non-destructive; the description adds the material economics and failure behavior itself: credits charged per audited domain, blocked/timed-out sites returning a free row with a reason, failed runs returned as an error carrying a run ID, and 24-hour cache reuse. That is exactly the context an agent needs before spending money.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single dense paragraph with the core action front-loaded and the disclaimers/billing pushed later, where they belong. It is long, but nearly every clause carries decision-relevant information (cost model, failure rows, conformance caveat) rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight optional parameters, no output schema, and a paid third-party dependency, the description covers what would otherwise be missing: result shape per row, score range, error semantics with run ID, cache behavior, and cost exposure. An agent can decide whether and how to call this without reading anything else.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds billing semantics the schema alone implies but does not emphasize — per-page charging for multi-page audits and per-domain charging when any compliance check is set. The standards mapping (ada→WCAG 2.1 AA, en301549→EAA) and German-only Impressum restriction are also restated in the description, reinforcing rather than adding to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource plus the implementation ('Audit websites for accessibility with axe-core in a real browser'), then enumerates exactly what comes back per domain: failing rules by impact, element counts, score, EAA signals, and optional presence checks. There are no siblings, so it only needs to be self-contained, and it is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Give one domain or a list' states the two operating modes, and the description explicitly limits scope by warning that automated checks find only a subset of WCAG failures and results are never a conformance claim. It also states prerequisites (APIFY_TOKEN, credit consumption) and that failures return a free row. It stops short of explicit when-not-to-use guidance beyond the conformance caveat.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools

audit_wcag_accessibilityA