Accessibility Agents

io.github.Community-AccessPublished by GitHub account Community-Accessv7.1.0Updated Oct 29, 2026

WCAG 2.2 scanners for web pages, Office, PDF, ePub and Markdown: contrast, axe, veraPDF and more.

Overview

AI-generated overview

Accessibility scanning MCP server that lets an assistant check web pages, Office files, PDFs, ePub and Markdown against WCAG 2.2 and PDF/UA rules.

What you can do
  • Check colors, headings, link text and form labels against WCAG guidelines
  • Scan and batch-scan Office, PDF, ePub and Markdown documents, extract metadata, and fix document metadata or headings
  • Run browser scans on live URLs: axe-core, accessibility tree, keyboard navigation, contrast and viewport reflow
  • Validate PDFs deeply with veraPDF and convert PDF forms to accessible HTML
  • Send Markdown, HTML or DOCX files to a remote GLOW service for audit, fix, convert and report
  • Read WCAG reference resources and use guided audit, component and criterion prompts, plus an audit cache
When to use it
Useful when you need to audit or remediate accessibility of documents and web pages, for example checking a PDF or Word file for PDF/UA or WCAG issues, or running axe-core and keyboard checks on a site during development.
Requirements
Runs locally over stdio via npx or a bundled entry point; Node.js LTS (22, 24 or 26) is required. Optional features need extra packages: playwright and @axe-core/playwright with Chromium for browser scans, pdf-lib for form conversion, and the veraPDF CLI with Java 11+ for deep PDF validation. HTTP mode needs npm install and uses PORT, A11Y_MCP_HOST and A11Y_MCP_STATELESS.
Before you install
The GLOW bridge tools upload your Markdown, HTML or DOCX files to a remote endpoint (default letitglow.app, configurable via GLOW_API_BASE_URL) for audit, fix, convert and report. Fix tools modify document metadata and headings, and cache tools write audit results. Browser tools fetch live URLs. No authentication is declared, so a shared HTTP deployment is unprotected unless you restrict access.

Installation

In SourceWeft

  1. Open Accessibility Agents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

A11y Agent Team MCP Server

MCP (Model Context Protocol) server that provides 39 accessibility scanning tools over Streamable HTTP or stdio. Works with Claude Code, Claude Desktop, VS Code, the Copilot CLI and any MCP-compatible client. It is built on @modelcontextprotocol/sdk 1.32.2 and implements what that SDK provides (protocol revisions up to 2025-11-25); see the MCP standards page for where it stands against 2026-07-28.

In this repository, the MCP server lives in the top-level mcp-server/ directory. The main entry points are server.js (HTTP) and stdio.js (stdio).

What Works Out Of The Box

The MCP server is the executable part of document scanning. The skills (for PDF, pdf-accessibility and pdf-scan-config under skills/) tell the model when to scan; this server provides the actual scan_pdf_document tool.

What you installWhat you getPDF scanning works?
Skills onlyPDF scanning instructions in chatNo
Skills + MCP serverWorking scan_pdf_document toolYes
Skills + MCP server + veraPDFBaseline scan + deep PDF/UA validationYes

A plugin install launches dist/stdio.mjs, a single esbuild bundle of the stdio server and its dependencies, so it starts with no npm install (mcp.json, and mcpServers in .claude-plugin/plugin.json). Playwright, @axe-core/playwright and pdf-lib are left out of the bundle and stay optional; the tools that need them say how to install them. Run npm install in this folder only for the HTTP server (server.js) or to work on the source.

If you change the server's source, run npm run build here and commit the rebuilt dist/stdio.mjs: the bundle gate in npm run verify fails when the committed bundle differs from a fresh build.

Architecture

The server supports two transport modes:

ModeEntry PointTransportUse Case
HTTPserver.jsStreamable HTTP (stateful with a GET event stream by default; stateless with A11Y_MCP_STATELESS=1). The legacy HTTP+SSE transport is not offeredRemote clients, shared servers, CI/CD
stdiostdio.js (bundled as dist/stdio.mjs)stdin/stdoutClaude Desktop, plugin installs, local use

Both modes share the same tool implementations via server-core.js.

Quick Start

Before you start, make sure node --version reports a supported Node.js LTS line (26, 24 or 22) and that npm is available. The repository installer does not install Node.js; get it from https://nodejs.org/en/download.

bash
# stdio, from the bundle: no install needednode mcp-server/dist/stdio.mjs
# HTTP mode needs the dependenciescd mcp-servernpm installnpm start# -> http://127.0.0.1:3100/mcp

From npm, with no checkout (from 7.1.0, once published as @community-access/accessibility-agents-mcp; also listed in the MCP Registry as io.github.Community-Access/accessibility-agents):

bash
npx -y @community-access/accessibility-agents-mcpclaude mcp add accessibility-agents -- npx -y @community-access/accessibility-agents-mcp

The npm package is the stdio bundle alone. The browser and PDF form tools need their optional packages in the same node_modules, so for those install the server into a folder with them and run it from there: npm install @community-access/accessibility-agents-mcp playwright @axe-core/playwright pdf-lib, npx playwright install chromium, then npx accessibility-agents-mcp.

For a PDF-only walkthrough, see PDF-QUICKSTART.md.

Prerequisite Matrix

Each class, with requirement, needed for and required.

ClassRequirementNeeded ForRequired?
RuntimeNode.js LTS (26, 24 or 22)Running the MCP serverYes
Runtimenone for the stdio bundledist/stdio.mjs carries @modelcontextprotocol/sdk and zod inside itNo
HTTP or developmentnpm, then npm install in this folder (@modelcontextprotocol/sdk, zod, express)The HTTP server (server.js), running the unbundled source and the testsOnly for those
ClientMCP-compatible clientCalling the server toolsYes
Optional featureJava 11+ + verapdfDeep PDF validation with run_verapdf_scanNo
Optional featureplaywright, @axe-core/playwright, ChromiumBrowser-based scanning toolsNo
Optional featurepdf-libconvert_pdf_form_to_htmlNo
Installer-onlygitCloning the repositoryNo

Python is not required to run the MCP server or to install the package.

Local Vs Shared Server

You can run this MCP server either locally on your own machine or as a shared HTTP service.

ModeWhere it runsBest for
Local stdioYour machine, started by the clientClaude Desktop and local-only use
Local HTTPYour machine on 127.0.0.1VS Code Copilot, local testing, debugging
Shared HTTPA server or containerTeam use, CI/CD, remote clients

For most users, start locally first. The default HTTP binding is 127.0.0.1, so it is not exposed to the network unless you deliberately change the host.

Configuration

Each environment variable, with its default and description.

Environment VariableDefaultDescription
PORT3100HTTP server port
A11Y_MCP_HOST127.0.0.1Bind address
A11Y_MCP_STATELESS(unset)Set to 1 for stateless mode
GLOW_API_BASE_URLhttps://letitglow.app/mcpEndpoint the GLOW bridge tools call

Stateful vs Stateless

  • Stateful (default): Sessions persist across requests (Mcp-Session-Id), and a GET request opens a server-sent event stream for that session. Best for interactive use. The 2026-07-28 MCP revision removes sessions and the GET endpoint; this mode follows the SDK.
  • Stateless: Each request creates a fresh server instance. No sessions, POST only. Best for CI/CD and serverless deployments.

Client Configuration

Claude Desktop (claude_desktop_config.json)

Claude Desktop starts local servers from claude_desktop_config.json (Settings, Developer, Edit Config), using stdio:

json
{  "mcpServers": {    "a11y-agent-team": {      "command": "node",      "args": ["/path/to/mcp-server/dist/stdio.mjs"]    }  }}

Remote HTTP servers are added in Claude Desktop as custom connectors rather than in this file; see https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp.

Claude Code

The plugin registers the server for you. Without the plugin:

bash
claude mcp add --transport stdio a11y-agent-team -- node /path/to/mcp-server/dist/stdio.mjs

VS Code (.vscode/mcp.json)

json
{  "servers": {    "a11y-agent-team": {      "type": "http",      "url": "http://127.0.0.1:3100/mcp"    }  }}

Using GLOW Bridge Tools

The GLOW bridge tools are part of this MCP server. You do not register a second MCP server for GLOW.

Default behavior

  • The bridge targets https://letitglow.app/mcp by default.
  • You can call glow_health_check immediately after starting this server.

Use a different GLOW endpoint

Option 1: set server environment variable before startup:

bash
# Linux/macOSexport GLOW_API_BASE_URL="https://letitglow.app/mcp"npm start
powershell
# Windows PowerShell$env:GLOW_API_BASE_URL = "https://letitglow.app/mcp"npm start

Option 2: pass baseUrl per tool call (for one-off testing):

  • glow_health_check with baseUrl
  • glow_audit_document with baseUrl
  • glow_fix_document with baseUrl
  • glow_convert_document with baseUrl
  • glow_generate_report with baseUrl

Example prompts after connection

  • Run glow_health_check
  • Audit ./docs/sample.md with glow_audit_document using format markdown
  • Convert ./docs/sample.md from markdown to html with glow_convert_document
  • Generate an html report for ./docs/sample.md with glow_generate_report

PDF-Only Quick Start

If your immediate goal is only PDF accessibility scanning, this is the smallest working path:

  1. Install a Node.js LTS release (26, 24 or 22).
  2. Open this folder: mcp-server/
  3. Run npm install
  4. Start the server with npm start
  5. Point your MCP client at http://127.0.0.1:3100/mcp
  6. Install the skills (see Getting started) if you want the guided PDF workflow in chat

Minimum files for the MCP side:

  • package.json
  • server.js
  • server-core.js
  • stdio.js
  • tools/

If you also want the chat workflow layer, add:

  • the pdf-accessibility and pdf-scan-config skills (skills/pdf-accessibility/, skills/pdf-scan-config/), installed with the rest of the package
  • templates/pdf-config-moderate.json copied to your project as .a11y-pdf-config.json (optional)

Available Tools

Core Tools

Each tool, with its description.

ToolDescription
check_contrastCalculate WCAG contrast ratio between two colors
get_accessibility_guidelinesGet WCAG AA guidelines for component types
check_heading_structureAnalyze HTML heading hierarchy
check_link_textDetect ambiguous or missing link text
check_form_labelsCheck form inputs for accessible labels

Document Tools

Each tool, with its description.

ToolDescription
scan_office_documentScan .docx/.xlsx/.pptx for accessibility issues
scan_pdf_documentScan PDF using PDF/UA checks
scan_epub_documentScan .epub files for EPUB Accessibility 1.1 conformance
extract_document_metadataExtract accessibility-relevant metadata
batch_scan_documentsScan multiple documents in one call
fix_document_metadataFix document metadata (title, language, author)
fix_document_headingsFix heading structure in documents

GLOW Bridge Tools

Each tool, with its description.

ToolDescription
glow_health_checkCheck health of a GLOW endpoint (default: https://letitglow.app/mcp)
glow_audit_documentUpload a markdown/html/docx file to GLOW and run /audit
glow_fix_documentUpload a markdown/html/docx file to GLOW and run /fix
glow_convert_documentUpload a markdown/html/docx file to GLOW and run /convert
glow_generate_reportUpload a markdown/html/docx file to GLOW and run /report

Advanced Tools (Optional Dependencies)

Each tool, with its requires and description.

ToolRequiresDescription
run_axe_scanplaywright, @axe-core/playwrightRun axe-core against a live URL
run_playwright_a11y_treeplaywrightCapture accessibility tree
run_playwright_keyboard_scanplaywrightTest keyboard navigation
run_playwright_contrast_scanplaywrightVisual contrast analysis
run_playwright_viewport_scanplaywrightTest reflow at multiple widths
run_verapdf_scanveraPDF CLIPDF/UA-1 (default), PDF/UA-2 or PDF/A validation, chosen with flavour (SARIF output)
convert_pdf_form_to_htmlpdf-libConvert PDF forms to accessible HTML

Markdown Tools

Each tool, with its description.

ToolDescription
scan_markdown_documentScan markdown files for accessibility issues (links, alt text, headings, tables, emoji)

Caching Tools

Each tool, with its description.

ToolDescription
check_audit_cacheCheck if a cached audit result exists for a file
update_audit_cacheStore or update an audit result in the cache

Installing Optional Dependencies

bash
# Playwright + axe-core (for web scanning)npm install playwright @axe-core/playwrightnpx playwright install chromium
# pdf-lib (for PDF form conversion)npm install pdf-lib
# veraPDF (external CLI)# Download from https://verapdf.org/software/

Actionable veraPDF Setup

veraPDF is optional. The built-in scan_pdf_document tool works without it. Install veraPDF when you need deeper PDF/UA validation than the built-in heuristic scan provides.

What veraPDF is for

  • Validate PDF/UA conformance more deeply than the built-in scanner
  • Confirm structure and metadata issues against a dedicated PDF validator
  • Use as a second pass after baseline scanning

What veraPDF is not for

  • It is not required for baseline PDF scanning
  • It is not the primary remediation workflow in this repository
  • Do not assume verapdf --fix is part of the supported workflow here

Install veraPDF

veraPDF requires Java 11 or later.

Windows

Install Java first if it is not already present:

bash
winget install --exact --id EclipseAdoptium.Temurin.21.JRE

Then install veraPDF using Chocolatey if available:

bash
choco install verapdf

If Chocolatey is not part of your environment, use the manual installer from https://docs.verapdf.org/install/.

macOS

bash
brew install verapdf

Manual download

Download from https://docs.verapdf.org/install/ and make sure verapdf is available on your PATH.

Verify veraPDF

bash
verapdf --version

On Windows, restart your terminal or editor after installing Java or veraPDF so the updated PATH is picked up.

Use veraPDF directly

bash
verapdf --flavour ua1 --format text path/to/file.pdf

Use veraPDF through this MCP server

Once the server is running and veraPDF is installed on the same machine, an MCP client can call run_verapdf_scan.

Example natural-language requests:

  • Run a deep PDF/UA scan on report.pdf using veraPDF
  • Validate brochure.pdf with veraPDF and summarize the failures

The tool will return installation guidance if verapdf is not installed.

For more background, see veraPDF integration.

Health Check

bash
curl http://127.0.0.1:3100/health# {"status":"ok","name":"a11y-agent-team","version":"7.1.0","mode":"stateful"}

MCP Prompts

Pre-built prompt templates that guide the model through accessibility workflows.

PromptArgumentsDescription
audit-pageurl (required), level (optional: A/AA/AAA)Structured WCAG audit instruction; walks through axe-core, heading, link, form, keyboard, and contrast scans
check-componentcomponent (required)Component-specific review using built-in guidelines (modal, tabs, accordion, combobox, carousel, form, live-region, navigation, general)
explain-wcagcriterion (required)Explain a WCAG criterion with practical examples, common violations, and testing guidance

MCP Resources

Read-only data endpoints for accessibility reference material. The two with a {...} parameter are resource templates: a client lists or completes them and reads a concrete address such as a11y://guidelines/modal.

Resource URIDescription
a11y://guidelines/{component}Component accessibility guidelines in Markdown (modal, tabs, accordion, combobox, carousel, form, live-region, navigation, general)
a11y://toolsAuto-generated list of all registered tools with descriptions
a11y://config/{profile}Scan configuration templates as JSON (strict, moderate, minimal)

Security

  • Path traversal prevention: File operations validate paths against home directory and CWD boundaries (CWE-22)
  • Symlink resolution: Write operations resolve symlinks to prevent escape (CWE-59)
  • SSRF protection: URL-based tools validate schemes (http/https only)
  • Command injection prevention: External commands use execFile (not exec) with argument arrays
  • File size limits: Documents capped at 100 MB, batch operations at 50 files
  • Local binding: Server binds to 127.0.0.1 by default (not exposed to network)

Deployment

Docker

dockerfile
FROM node:24-slimWORKDIR /appCOPY package.json .RUN npm installCOPY . .EXPOSE 3100CMD ["node", "server.js"]

Systemd

ini
[Unit]Description=A11y Agent Team MCP ServerAfter=network.target
[Service]Type=simpleExecStart=/usr/bin/node /opt/a11y-mcp/server.jsEnvironment=PORT=3100Restart=on-failure
[Install]WantedBy=multi-user.target

License

MIT. See LICENSE in the repository root.

Source: mcp-server/README.md at commit 7597f1a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v7.1.0LatestOct 29, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts