MCP Server By TestMu AI

Get Accessibility Report

getAccessibilityReport

Runs an accessibility scan on the given URLs and returns the issues found. Pass urls to start a scan, or testId to re-read a scan that already ran; exactly one of the two. Results arrive in issueDetails: allIssues (most-severe-first, one page at a time), rules (name and reference link per rule id, listed once), pages (every scanned page with its score and issue count), failedRules (per-rule totals for the whole scan) and pagination. Each issue carries its own howToFix and criteria, measured for that element - two issues sharing a rule can have different causes and fixes. While pagination.nextOffset is not null the results are incomplete: call again with the testId from the response plus that offset, keeping the same filters, until it is null. Page with testId, never by passing urls again - that starts a new scan, costs another run, and can return a different set of issues whose offsets do not line up. a11yReportLink is the dashboard URL and needs a login; shareableLink is public and is only returned by the original scan.

Input Schema

TableJSON Schema

Name	Required	Description
`urls`	No	List of URLs to scan. Starts a new scan. Provide either urls or testId, not both.
`limit`	No	Maximum issues to return in this response (default 50, max 200).
`offset`	No	Index to start from within the filtered, severity-sorted issue list. Pass the nextOffset from a previous response, together with that response's testId, to page through results.
`testId`	No	Re-read an existing scan by its testId (as returned in a previous response) instead of running a new one. Use this to page through results with offset.
`pageUrl`	No	Only return issues found on this scanned page. Must exactly match one of the URLs in issueDetails.pages.
`severity`	No	Only return issues of this impact level. Omit to get all severities.
`include_rules`	No	Return the full rule catalog (about 11 KB) instead of the default ruleCatalog summary of counts per category and disabled rule ids.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

addedInput schema / properties / include_rules

Added value: +{
+  "description": "Return the full rule catalog (about 11 KB) instead of the default ruleCatalog summary of counts per category and disabled rule ids.",
+  "type": "boolean"
+}

First observedOct 5, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) signal a non-read compute action with external effects; the description adds the crucial cost implication ("costs another run"), the auth distinction between a11yReportLink (needs login) and shareableLink (public, scan-only), and the pagination completion contract. This is substantial context the structured fields do not carry.

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

Conciseness5/5

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

Purpose is front-loaded, then output shape, then pagination workflow, then link caveats. Despite its length, every sentence carries operational information (offset alignment, re-scan cost, link auth) that an agent needs; nothing is padding.

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?

There is no output schema, so the description bears full responsibility for return-value semantics, and it delivers: it names issueDetails sub-fields (allIssues, rules, pages, failedRules, pagination), explains severity ordering and per-element howToFix/criteria, and defines the pagination termination condition. An agent has everything needed to call and consume this tool correctly.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning on top: it clarifies the urls/testId exclusivity, the testId+offset pairing for paging, and that filters must stay constant across pages. It leaves some params (severity, pageUrl, include_rules) to the schema, which documents them adequately.

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?

States a specific verb+resource ("Runs an accessibility scan on the given URLs") and immediately distinguishes its two operating modes: starting a scan via urls versus re-reading via testId. An agent understands both what it does and the dual nature of the tool without opening the schema.

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

Usage Guidelines5/5

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

Explicitly states the exactly-one-of constraint between urls and testId, explains when to use each, and proactively warns that re-passing urls to page starts a new scan, costs another run, and yields misaligned offsets. This is precisely the conditional guidance that prevents incorrect invocation.

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

All MCP Server By TestMu AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?