Local MCP capabilities provider for Expo
Accessibility Agents is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
WCAG 2.2 scanners for web pages, Office, PDF, ePub and Markdown: contrast, axe, veraPDF and more.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user accessibility-agents-mcp '--' npx -y @community-access/accessibility-agents-mcp
# 2 — ask your agent for something these tools do
# scan_epub_document, save_audit_result, list_audit_history and 36 more
Accessibility Agents costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Accessibility Agents as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user accessibility-agents-mcp '--' npx -y @community-access/accessibility-agents-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
39 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Scan an .epub for EPUB Accessibility 1.1 conformance, reading order, navigation and metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the .epub file |
| reportPath | string | no | Optional path to write a markdown accessibility report |
| sarifPath | string | no | Optional path to write SARIF 2.1.0 output |
Save a scan result to the audit history so later runs can show a delta and compliance evidence stays in the repository.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | Type of scan that produced these results |
| target | string | yes | Target that was scanned (URL, file path, or folder path) |
| score | number | no | Overall accessibility score (0-100) |
| grade | string | no | Letter grade (A-F) |
| findingCount | number | yes | Total number of findings |
| errorCount | number | no | Number of error-severity findings |
| warningCount | number | no | Number of warning-severity findings |
| findings | array | no | Array of individual findings (optional, for detailed storage) |
| toolVersion | string | no | Version of the scanning tool |
| retention | number | no | Max audits to keep per target (default: …) |
List stored accessibility audit results from .a11y-history/.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by scan type |
| target | string | no | Filter by target (exact match on path/URL) |
| limit | number | no | Max results to return (default: 20, newest first) |
Retrieve a specific stored audit result by its ID. Returns the full audit record including all findings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| auditId | string | yes | Audit ID (filename without .json extension, from list_audit_history) |
Remove old audit results beyond the retention limit for each target.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| retention | number | no | Max audits to keep per target (default: …) |
Check health of a GLOW API endpoint (defaults to https://letitglow.app/mcp).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | no | Optional GLOW API base URL |
| timeoutMs | integer | no | — |
Upload a document to GLOW and run accessibility audit (/audit). Supports markdown, html, and docx.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to local file |
| format | string | yes | Document format |
| baseUrl | string | no | Optional GLOW API base URL |
| timeoutMs | integer | no | — |
Upload a document to GLOW and run auto-fix workflow (/fix). Supports markdown, html, and docx.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to local file |
| format | string | yes | Document format |
| baseUrl | string | no | Optional GLOW API base URL |
| timeoutMs | integer | no | — |
Upload a document to GLOW and convert format (/convert). Supports markdown, html, and docx.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to local file |
| fromFormat | string | yes | Source format |
| toFormat | string | yes | Target format |
| baseUrl | string | no | Optional GLOW API base URL |
| timeoutMs | integer | no | — |
Upload a document to GLOW and generate report output (/report). Supports markdown, html, and docx.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to local file |
| format | string | yes | Document format |
| reportType | string | no | Report type (default: json) |
| baseUrl | string | no | Optional GLOW API base URL |
| timeoutMs | integer | no | — |
Scan a markdown file for link text, alt text, heading order, table and emoji accessibility issues.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the .md file |
| reportPath | string | no | Optional path to write a markdown accessibility report |
Extract form fields from a PDF and generate an accessible HTML representation. Useful for reviewing PDF form accessibility or migrating paper forms to web.
No parameter schema on file.
Run an axe-core scan against a URL or HTML file and return the violations as findings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to scan (http or https) |
| tags | array | no | axe-core tags to filter by (default: ["wcag2a", "wcag2aa", "wcag21a", "wcag21aa", "wcag22aa"], every WCAG 2.2 A and AA rule) |
| include | array | no | CSS selectors to include in scan |
| exclude | array | no | CSS selectors to exclude from scan |
Capture the accessibility tree of a page via Playwright. Shows how screen readers perceive the page structure.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to analyze |
| root | string | no | CSS selector for subtree root |
Test keyboard navigation by tabbing through all interactive elements on a page. Reports focus order, focus visibility, and keyboard traps.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to test |
| maxTabs | number | no | Maximum Tab presses (default: 50) |
Scan a page for text elements that fail WCAG AA contrast requirements by sampling computed styles.
No parameter schema on file.
Load the page at 320, 768, 1024 and 1280 CSS pixels wide and report horizontal scrolling, a WCAG 1.4.10 Reflow check that does not test zoom or text resize.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to test |
Render a complete audit report from findings JSON. Produces every required section, computes the score and grade, and embeds the merged findings so the next run can show a delta.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| findings | array | yes | Findings payloads, each matching skills/a11y-core/schemas/findings.schema.json. |
| template | string | no | Which report shape to render. |
| outputPath | string | no | Where to write the report. Defaults to the template's standard filename in the working directory. |
Return the score history for one target, with direction, delta and finding velocity, so a trend can be reported.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | Target to compute trend for (URL or file path) |
| limit | number | no | Max historical scans to include (default: 20) |
Health check for veraPDF CLI. Auto-detects installation, reports version,
No parameter schema on file.
Validate a PDF against PDF/UA with veraPDF and return the failed checks as findings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the PDF file |
| flavour | string | no | veraPDF validation flavour (default: "ua1" for PDF/UA-1) |
| sarifPath | string | no | Optional path to write SARIF 2.1.0 output for CI/code scanning integration |
Calculate WCAG contrast ratio between two colors. Returns the ratio and whether it passes AA for normal text (4.5:1), large text (3:1), and UI components (3:1).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| foreground | string | yes | Foreground color as hex (e.g. "#1a1a1a" or "#fff") |
| background | string | yes | Background color as hex (e.g. "#ffffff" or "#000") |
Calculate APCA lightness contrast between two colours, an experimental perceptual method that no WCAG standard, and not the current WCAG 3.0 draft, includes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| foreground | string | yes | Text color as hex (e.g. "#1a1a1a" or "#fff") |
| background | string | yes | Background color as hex (e.g. "#ffffff" or "#000") |
Get detailed WCAG AA accessibility guidelines for a specific component type. Returns requirements, code examples, and common mistakes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| component | string | yes | The type of component to get guidelines for |
Analyze HTML content for heading hierarchy issues: skipped levels, multiple H1s, missing H1, empty headings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | HTML content to analyze |
Analyze HTML for ambiguous or missing link text. Checks for 'click here', 'read more', empty links.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | HTML content to analyze |
Analyze HTML form inputs for missing accessible labels. Checks <label for>, aria-label, aria-labelledby, and title.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | HTML content to analyze |
Scan a .docx, .xlsx, or .pptx file for accessibility issues. Checks title, language, alt text, headings, table headers, and more.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the Office document |
Scan a PDF file for accessibility issues using PDF/UA checks. Checks tagging, structure, language, alt text, bookmarks, forms, and more.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the PDF file |
| reportPath | string | no | File path to write a markdown accessibility report |
| sarifPath | string | no | File path to write SARIF 2.1.0 output |
Extract accessibility-relevant metadata from an Office document or PDF. Returns title, author, language, page count, and accessibility property health.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the document file (.docx, .xlsx, .pptx, or .pdf) |
Scan multiple Office and PDF documents for accessibility issues in a single call. Returns a summary with per-file results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePaths | array | yes | Array of absolute file paths to scan (max 50) |
Fix common metadata accessibility issues in Office documents: missing title, missing language, missing author. Returns a report of changes made.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the document (.docx, .xlsx, .pptx) |
| title | string | no | Document title to set |
| language | string | no | Document language to set (BCP 47 tag, e.g. "en-US") |
| author | string | no | Document author to set |
Analyze and report heading structure issues in Office documents with fix instructions. Detects skipped levels, missing Heading 1, visual-only formatting, and provides remediation steps.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the document (.docx) |
Check whether a cached audit result exists and is still fresh for this target.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePaths | array | yes | Array of file paths to check against the cache |
| cacheFile | string | no | Path to cache file (default: .a11y-cache.json in project root) |
| useContentHash | boolean | no | Use SHA-256 content hash instead of size+mtime (more reliable but slower). Default: false |
| maxAgeDays | number | no | Treat entries older than this many days as expired and needing re-scan. Default: no expiry |
Update the component audit cache (.a11y-cache.json) after scanning files. Stores file hashes, finding counts, severity breakdown, and scan timestamp so unchanged files can be skipped on re-audit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entries | array | yes | Array of scan results to cache |
| cacheFile | string | no | Path to cache file (default: .a11y-cache.json in project root) |
| useContentHash | boolean | no | Use SHA-256 content hash instead of size+mtime. Default: false |
Simulate how a color pair looks under different types of color vision deficiency (protanopia, deuteranopia, tritanopia, achromatopsia). Returns simulated colors and whether distinction is maintained.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| colors | array | yes | Array of hex colors to compare (e.g. ['#FF0000', '#00FF00']) |
Estimate the reading level of a passage and report whether it meets the requested grade.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text content to analyze |
Validate a WebVTT or SRT caption file for syntax errors, timing overlaps, excessive caption rate, and missing speaker identification. Helps ensure media accessibility compliance (WCAG 1.2.2, 1.2.4).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | Absolute path to the .vtt or .srt caption file |
Generate a W3C or EU model accessibility statement from provided information. Outputs a Markdown document ready for publishing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| organization | string | yes | Organization name |
| websiteUrl | string | yes | Website URL covered by the statement |
| contactEmail | string | yes | Accessibility feedback contact email |
| conformanceLevel | string | no | Target WCAG level (default: AA) |
| conformanceStatus | string | yes | Overall conformance status |
| format | string | no | Statement format: w3c (default) or eu |
| assessmentDate | string | no | Date of last assessment (ISO format) |
| assessmentMethod | string | no | How the assessment was conducted |
| knownLimitations | array | no | Known accessibility limitations |
| technologies | array | no | Technologies relied upon (e.g. HTML5, CSS3, WAI-ARIA) |
| compatibleWith | array | no | Browsers and assistive technologies tested |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Accessibility Agents or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 7.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Accessibility Agents can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.