io.github.aditya-ariosity/wcag-accessibility
NPM · WCAG-ACCESSIBILITY-MCP
A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.
Available components
Last scanned (3 hours ago)
Scores higher than 78% of npm servers
Category Testing and QA
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security90
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects basic-ftp 5.3.1, reached via puppeteer-core > @puppeteer/browsers > proxy-agent > pac-proxy-agent > get-uri > basic-ftp. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 50 of 171 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 58 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 956 tokens (~136/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage90
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 71% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Oct 26 +1
- Stability: 0.97 → pass security
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +1
- Security disclosure: unverified → pass ▲ functional
- 12 Oct 26 0
- Security disclosure: pass → unverified ▼ functional
- 3 Oct 26 −3
- Stability: pass → 0.80 functional
- 2 Oct 26 −2
- CVE-2026-102990 affects this package: high ▼ security
- Known CVEs: partial → fail ▼ security
- CVE-2026-19693 no longer affects this package ▲ security
- CVE-2026-56876 no longer affects this package ▲ security
- Stability: 0.97 → pass security
- 1 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 17 Oct 2026 · Analysed npm/wcag-accessibility-mcp@0.1.6
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 3 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-c475-qrg2-pj4r | CVE-2026-102990 | high | yes | |
| GHSA-7pqw-9j4j-h8q3 | CVE-2026-19693 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:H | no |
| GHSA-jmr9-qjv8-65gv | CVE-2026-56876 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 171 packages
| Packages resolved | 171 |
|---|---|
| Stale | 50 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_file Audit a local HTML file ~142
Render a local .html or .htm file beneath the configured allowed root and return accessibility findings and corrections. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| filePath | string | yes | Absolute path, or path relative to the server working directory, to an HTML file. |
| height | integer | – | Viewport height in CSS pixels. |
| maxIssues | integer | – | Maximum violation groups returned; summary totals still cover the full run. |
| maxNodesPerIssue | integer | – | Maximum affected elements returned per rule. |
| standard | string | – | WCAG ruleset to test. Use best-practice to include additional axe guidance. |
| width | integer | – | Viewport width in CSS pixels. |
No output schema declared.
No examples provided.
audit_html Audit an HTML document ~160
Render supplied HTML in an isolated headless browser and return WCAG findings plus evidence and suggested corrections. Use for generated UI before it is hosted. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| baseUrl | string | – | Optional http(s) base URL used to resolve relative assets. |
| height | integer | – | Viewport height in CSS pixels. |
| html | string | yes | Complete HTML document or fragment to render and test. |
| maxIssues | integer | – | Maximum violation groups returned; summary totals still cover the full run. |
| maxNodesPerIssue | integer | – | Maximum affected elements returned per rule. |
| standard | string | – | WCAG ruleset to test. Use best-practice to include additional axe guidance. |
| width | integer | – | Viewport width in CSS pixels. |
No output schema declared.
No examples provided.
audit_url Audit a rendered URL ~147
Load a public or local web page in headless Chromium, run axe-core, and return prioritized WCAG findings, DOM evidence, computed styles, and contrast corrections. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| height | integer | – | Viewport height in CSS pixels. |
| maxIssues | integer | – | Maximum violation groups returned; summary totals still cover the full run. |
| maxNodesPerIssue | integer | – | Maximum affected elements returned per rule. |
| standard | string | – | WCAG ruleset to test. Use best-practice to include additional axe guidance. |
| url | string | yes | Absolute http:// or https:// URL to render and test. |
| width | integer | – | Viewport width in CSS pixels. |
No output schema declared.
No examples provided.
check_contrast Check a color pair ~118
Calculate the WCAG contrast ratio for foreground and background colors and determine whether the pair passes for the supplied text size and weight.
| Name | Type | Req | Description |
|---|---|---|---|
| background | string | yes | Background CSS sRGB color such as white, #ffffff, rgb(), hsl(), or color(srgb ...). |
| fontSizePx | number | – | – |
| fontWeight | integer | – | – |
| foreground | string | yes | Foreground CSS sRGB color such as white, #767676, rgb(), hsl(), or color(srgb ...). |
| level | string | – | – |
No output schema declared.
No examples provided.
explain_issue Explain an accessibility rule ~49
Return implementation-focused remediation steps and the axe rule reference for a rule ID found in an audit.
| Name | Type | Req | Description |
|---|---|---|---|
| ruleId | string | yes | axe rule ID such as color-contrast, button-name, or label. |
No output schema declared.
No examples provided.
get_wcag_checklist Get the complete WCAG requirement checklist ~95
Return every success criterion required by a WCAG 2.0, 2.1, or 2.2 A/AA/AAA profile, with W3C references, axe rule mappings, and explicit automated-partial versus manual coverage. Use this to plan the checks that a browser audit cannot complete.
| Name | Type | Req | Description |
|---|---|---|---|
| evaluation | string | – | – |
| principle | string | – | – |
| standard | string | – | – |
No output schema declared.
No examples provided.
suggest_contrast_fix Suggest a passing color ~131
Find the nearest black-or-white-directed foreground or background adjustment that reaches the selected WCAG contrast threshold. Returns a mathematical candidate, not an automatic edit.
| Name | Type | Req | Description |
|---|---|---|---|
| adjust | string | – | – |
| background | string | yes | Background CSS sRGB color such as white, #ffffff, rgb(), hsl(), or color(srgb ...). |
| fontSizePx | number | – | – |
| fontWeight | integer | – | – |
| foreground | string | yes | Foreground CSS sRGB color such as white, #767676, rgb(), hsl(), or color(srgb ...). |
| level | string | – | – |
No output schema declared.
No examples provided.
How do I install the io.github.aditya-ariosity/wcag-accessibility MCP server?
io.github.aditya-ariosity/wcag-accessibility runs locally as an npm package, launched with npx -y wcag-accessibility-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · wcag-accessibility-mcp
claude mcp add aditya-ariosity-wcag-accessibility -- npx -y wcag-accessibility-mcp
What is the io.github.aditya-ariosity/wcag-accessibility MCP server?
io.github.aditya-ariosity/wcag-accessibility is an MCP server listed in the public MCP registry as io.github.aditya-ariosity/wcag-accessibility. A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits. This page covers its npm package (wcag-accessibility-mcp).
Is the io.github.aditya-ariosity/wcag-accessibility MCP server safe to use?
io.github.aditya-ariosity/wcag-accessibility scores 83 out of 100 on VerifyMCP. We recorded 3 known advisories against it as of 17 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.aditya-ariosity/wcag-accessibility MCP server expose?
io.github.aditya-ariosity/wcag-accessibility exposes 7 tools: audit_url, audit_html, audit_file, check_contrast, suggest_contrast_fix, and 2 more. Their descriptions and schemas cost roughly 842 tokens of context every time the server is loaded.
Is the io.github.aditya-ariosity/wcag-accessibility MCP server still maintained?
io.github.aditya-ariosity/wcag-accessibility is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.aditya-ariosity/wcag-accessibility MCP server under?
io.github.aditya-ariosity/wcag-accessibility declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.