Check public web pages for common WCAG 2.2 accessibility issues from your MCP client. The free scan_url tool needs no account and returns a score, severity breakdown, WCAG references, affected elements and fix guidance. Automated checks do not establish conformance; manual review is still required. Optional authenticated tools support monitoring your own sites. Documentation: https://allyproof.com/docs/mcp
Scored across 1 tool
There is only one tool, so there is no possibility of tool overlap or misselection. Its purpose is clearly and narrowly defined.
The single tool follows a clear verb_noun convention: scan_url. With only one name, there is no inconsistency to evaluate.
One tool is thin for a server framed as an accessibility product; it only supports single-page scans. It is appropriately focused for that narrow action, but the surface feels minimal.
The core single-page scan operation is well covered, including score, severity, violations, WCAG criteria, and fixes. Minor gaps remain around batch scanning, site-wide crawling, or configurable audit options.
Scan a single web page for WCAG 2.2 AA accessibility violations (axe-core + HTML_CodeSniffer + APCA). Returns a score (0-100), a severity breakdown, and up to 20 violations, each with WCAG criteria, description, and how to fix. Works for any public URL, no account needed. Automated testing detects common WCAG failure patterns; it cannot establish conformance, and no finding is not evidence of conformance. Determining conformance also needs manual review.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full URL to scan, e.g. https://example.com/pricing | |
| fresh | No | Authenticated callers only: bypass the 24-hour cache and run a new scan. Use for CI/release verification. |
| Name | Required | Description |
|---|---|---|
| id | Yes | Unique scan id; use with report_url. |
| url | Yes | The URL that was scanned. |
| note | Yes | Coverage/limitation disclaimer. |
| grade | Yes | Letter grade derived from score. |
| scope | Yes | Always "single_page" for this tool. |
| score | Yes | Accessibility score, 0-100. |
| cached | No | Present and true when served from the 24h per-URL cache. |
| summary | Yes | Severity roll-up. |
| report_url | Yes | Shareable JSON report for this scan id. |
| scanned_at | Yes | ISO-8601 scan timestamp. |
| violations | Yes | Up to 20 violation groups, most severe first. |
| get_full_site_scan_and_ai_fixes | Yes | Signup URL for full-site scans + AI fixes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world, non-destructive, but the description adds real value beyond them: output shape and the 20-violation cap, no-auth requirement, and the important epistemic caveat that absence of findings is not evidence of conformance. That caveat is the kind of trust-calibrating context annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with capability, then output shape, then access condition, then limitations. No filler; each sentence carries distinct information an agent needs.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a full output schema present, the description needn't detail return structure, yet it still summarizes it usefully. Combined with the access condition and conformance caveat, an agent has everything needed to call this correctly and interpret results honestly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both `url` and `fresh` are already documented, including the cache-bypass semantics. The description only reinforces that any public URL is acceptable and never mentions the caching/fresh behavior, so it adds little beyond the schema. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (scan) plus resource (single web page) and names the exact standard and engines (WCAG 2.2 AA, axe-core, HTML_CodeSniffer, APCA). An agent immediately knows what it does and that it is page-scoped, not site-wide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Works for any public URL, no account needed" gives a clear applicability condition, and the caveat about automated testing not establishing conformance tells the agent when the result is insufficient. There are no siblings to differentiate from, and no explicit when-not-to-use beyond that caveat.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
scan_url
Add one secure layer between your agents and this server.