Scans web pages, Office, PDF, ePub and Markdown files for WCAG accessibility issues and reports violations.
Also known as Community-Access/accessibility-agents, accessibility-agents, @community-access/accessibility-agents-mcp
- Stars
- 447
- Tools
- 39
- Downloads, 30 days
- 538
- Latest version
- 7.1.0
- Last commit
- Nov 13, 2026
- License
- MIT
What is Accessibility Agents MCP?
Accessibility Agents scans web pages, Office, PDF, ePub and Markdown files for WCAG accessibility issues and reports violations. It exposes 39 tools, such as check_contrast, check_apca_contrast, get_accessibility_guidelines.
Summary generated from the project's README
About Accessibility Agents MCP server
Scanning web pages, Office documents, PDFs, ePubs, and Markdown files for WCAG accessibility issues is what Accessibility Agents enables. This MCP server provides 39 specialized tools to identify and report violations across various digital formats. It is designed for developers and teams who need to ensure content meets accessibility standards using AI-driven clients like Claude Desktop, Claude Code, VS Code, or the Copilot CLI.
Users can run the server locally via stdio for desktop applications or host it as a shared HTTP service for CI/CD pipelines and remote teams. The server supports both stateful sessions for interactive use and stateless modes for serverless deployments. While the core server is lightweight, advanced capabilities like deep PDF/UA validation via veraPDF or browser-based scanning with Playwright and axe-core can be added through optional dependencies. It also includes bridge tools to interact with GLOW endpoints for auditing, fixing, and converting documents.
What you can do with it
- 1Audit PDF accessibilityScan a PDF document to check for PDF/UA conformance and accessibility violations.
- 2Validate Office documentsCheck Word, Excel, or PowerPoint files for accessibility problems.
- 3Check color contrastCalculate the WCAG contrast ratio between two specific colors.
Written from the project's README. Every use case is checked against a quote from it.
How to install Accessibility Agents MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Accessibility Agents MCP in Claude Code
$ claude mcp add accessibility-agents -- npx -y @community-access/accessibility-agents-mcpInstall Accessibility Agents MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"accessibility-agents": {
"command": "npx",
"args": [
"-y",
"@community-access/accessibility-agents-mcp"
]
}
}
}Install Accessibility Agents MCP in VS Code
.vscode/mcp.json
{
"servers": {
"accessibility-agents": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@community-access/accessibility-agents-mcp"
]
}
}
}Install Accessibility Agents MCP in VS Code CLI
$ code --add-mcp '{"name":"accessibility-agents","type":"stdio","command":"npx","args":["-y","@community-access/accessibility-agents-mcp"]}'Install Accessibility Agents MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"accessibility-agents": {
"command": "npx",
"args": [
"-y",
"@community-access/accessibility-agents-mcp"
]
}
}
}Install Accessibility Agents MCP in Codex
$ codex mcp add accessibility-agents -- npx -y @community-access/accessibility-agents-mcpInstall Accessibility Agents MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.accessibility-agents] command = "npx" args = ["-y", "@community-access/accessibility-agents-mcp"]
Install Accessibility Agents MCP in Gemini CLI
$ gemini mcp add -s user accessibility-agents npx -- -y @community-access/accessibility-agents-mcpInstall Accessibility Agents MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"accessibility-agents": {
"command": "npx",
"args": [
"-y",
"@community-access/accessibility-agents-mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @community-access/accessibility-agents-mcp 7.1.0 in an isolated container with no network and no keys. It answered and listed 39 tools.
Accessibility Agents MCP tools 39
Read from the server with tools/listcheck_contrastRead-onlyCalculate 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).
check_apca_contrastRead-onlyCalculate APCA lightness contrast between two colours, an experimental perceptual method that no WCAG standard, and not the current WCAG 3.0 draft, includes.
get_accessibility_guidelinesRead-onlyGet detailed WCAG AA accessibility guidelines for a specific component type. Returns requirements, code examples, and common mistakes.
check_heading_structureRead-onlyAnalyze HTML content for heading hierarchy issues: skipped levels, multiple H1s, missing H1.
check_link_textRead-onlyAnalyze HTML for ambiguous or missing link text. Checks for 'click here', 'read more', empty links.
check_form_labelsRead-onlyAnalyze HTML form inputs for missing accessible labels. Checks <label for>, aria-label, aria-labelledby, and title.
scan_office_documentRead-onlyScan a .docx, .xlsx, or .pptx file for accessibility issues. Checks title, language, alt text, headings, table headers, and more.
scan_pdf_documentRead-onlyScan a PDF file for accessibility issues using PDF/UA checks. Checks tagging, structure, language, alt text, bookmarks, forms, and more.
extract_document_metadataRead-onlyExtract accessibility-relevant metadata from an Office document or PDF. Returns title, author, language, page count, and accessibility property health.
batch_scan_documentsRead-onlyScan multiple Office and PDF documents for accessibility issues in a single call. Returns a summary with per-file results.
run_axe_scanRead-onlyRun an axe-core scan against a URL or HTML file and return the violations as findings.
run_playwright_a11y_treeRead-onlyCapture the accessibility tree of a page via Playwright. Shows how screen readers perceive the page structure.
Show all 39 toolsShow fewer tools
run_playwright_keyboard_scanRead-onlyTest keyboard navigation by tabbing through all interactive elements on a page. Reports focus order, focus visibility, and keyboard traps.
run_playwright_contrast_scanRead-onlyScan a page for text elements that fail WCAG AA contrast requirements by sampling computed styles.
run_playwright_viewport_scanRead-onlyLoad 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.
run_verapdf_scanRead-onlyValidate a PDF against PDF/UA with veraPDF and return the failed checks as findings.
check_verapdf_installationRead-onlyHealth check for veraPDF CLI. Auto-detects installation, reports version, checks Java dependency, and provides platform-specific installation guidance if missing.
convert_pdf_form_to_htmlActionExtract form fields from a PDF and generate an accessible HTML representation. Useful for reviewing PDF form accessibility or migrating paper forms to web.
scan_epub_documentRead-onlyScan an .epub for EPUB Accessibility 1.1 conformance, reading order, navigation and metadata.
scan_markdown_documentRead-onlyScan a markdown file for link text, alt text, heading order, table and emoji accessibility issues.
glow_health_checkRead-onlyCheck health of a GLOW API endpoint (defaults to `https://letitglow.app/mcp`).
glow_audit_documentRead-onlyUpload a document to GLOW and run accessibility audit (/audit). Supports markdown, html, and docx.
glow_fix_documentActionUpload a document to GLOW and run auto-fix workflow (/fix). Supports markdown, html, and docx.
glow_convert_documentActionUpload a document to GLOW and convert format (/convert). Supports markdown, html, and docx.
glow_generate_reportRead-onlyUpload a document to GLOW and generate report output (/report). Supports markdown, html, and docx.
save_audit_resultActionSave a scan result to the audit history so later runs can show a delta and compliance evidence stays in the repository.
list_audit_historyRead-onlyList stored accessibility audit results from .a11y-history/. Filter by scan type, target, or date range. Returns summaries with scores and finding counts.
get_audit_resultRead-onlyRetrieve a specific stored audit result by its ID. Returns the full audit record including all findings.
prune_audit_historyActionRemove old audit results beyond the retention limit for each target. Keeps the newest N audits per target and deletes the rest.
get_audit_trendRead-onlyReturn the score history for one target, with direction, delta and finding velocity, so a trend can be reported.
render_accessibility_reportActionRender 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.
fix_document_metadataActionFix common metadata accessibility issues in Office documents: missing title, missing language, missing author. Returns a report of changes made.
fix_document_headingsActionAnalyze and report heading structure issues in Office documents with fix instructions. Detects skipped levels, missing Heading 1, visual-only formatting, and provides remediation steps.
check_audit_cacheRead-onlyCheck whether a cached audit result exists and is still fresh for this target.
update_audit_cacheActionUpdate 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.
check_color_blindnessRead-onlySimulate how a color pair looks under different types of color vision deficiency (protanopia, deuteranopia, tritanopia, achromatopsia). Returns simulated colors and whether distinction is maintained.
check_reading_levelRead-onlyEstimate the reading level of a passage and report whether it meets the requested grade.
validate_caption_fileRead-onlyValidate 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).
generate_accessibility_statementActionGenerate a W3C or EU model accessibility statement from provided information. Outputs a Markdown document ready for publishing.
Configuration
GLOW_API_BASE_URL
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablecommunity-access/accessibility-agents is public and reachablegithub.com/community-access/accessibility-agents ↗Pass
- Package names this repository as its source@community-access/accessibility-agents-mcp names community-access/accessibility-agents as sourcenpmjs.com/package/@community-access/accessibility-agents-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @community-access/accessibility-agents-mcpnpmjs.com/package/@community-access/accessibility-agents-mcp ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/community-access/accessibility-agents ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @community-access/accessibility-agents-mcpPass
- No critical advisory in the package or its dependencies1 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model39 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubA11y 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 install | What you get | PDF scanning works? |
|---|---|---|
| Skills only | PDF scanning instructions in chat | No |
| Skills + MCP server | Working scan_pdf_document tool |
Yes |
| Skills + MCP server + veraPDF | Baseline scan + deep PDF/UA validation | Yes |
A plugin install launches dist/stdio.mjs (mcp.json, and mcpServers in .claude-plugin/plugin.json), which starts stdio.js. The stdio server is readable source with no dependencies outside Node: the protocol layer is lib/mcp-lite.js and argument checking is lib/schema.js, so it starts with no npm install, and the Claude plugin directory can read every file it ships. Playwright, @axe-core/playwright and pdf-lib 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.
There is no build step. The bundle gate in npm run verify fails if a shipped file imports a package, imports a file the plugin does not ship, or reaches 256 KiB. scripts/mcp-runtime-files.mjs lists what ships.
Architecture
The server supports two transport modes:
| Mode | Entry Point | Transport | Use Case |
|---|---|---|---|
| HTTP | server.js |
Streamable HTTP (stateful with a GET event stream by default; stateless with A11Y_MCP_STATELESS=1). The legacy HTTP+SSE transport is not offered |
Remote clients, shared servers, CI/CD |
| stdio | stdio.js (started by dist/stdio.mjs) |
stdin/stdout | Claude 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.
# stdio, from the bundle: no install needed
node mcp-server/dist/stdio.mjs
# HTTP mode needs the dependencies
cd mcp-server
npm install
npm 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):
npx -y @community-access/accessibility-agents-mcp
claude 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.
| Class | Requirement | Needed For | Required? |
|---|---|---|---|
| Runtime | Node.js LTS (26, 24 or 22) | Running the MCP server | Yes |
| Runtime | none for the stdio server | stdio.js uses only Node and lib/ |
No |
| HTTP or development | npm, then npm install in this folder (@modelcontextprotocol/sdk, zod, express) |
The HTTP server (server.js) and the tests |
Only for those |
| Client | MCP-compatible client | Calling the server tools | Yes |
| Optional feature | Java 11+ + verapdf |
Deep PDF validation with run_verapdf_scan |
No |
| Optional feature | playwright, @axe-core/playwright, Chromium |
Browser-based scanning tools | No |
| Optional feature | pdf-lib |
convert_pdf_form_to_html |
No |
| Installer-only | git |
Cloning the repository | No |
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.
| Mode | Where it runs | Best for |
|---|---|---|
| Local stdio | Your machine, started by the client | Claude Desktop and local-only use |
| Local HTTP | Your machine on 127.0.0.1 |
VS Code Copilot, local testing, debugging |
| Shared HTTP | A server or container | Team 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 Variable | Default | Description |
|---|---|---|
PORT |
3100 |
HTTP server port |
A11Y_MCP_HOST |
127.0.0.1 |
Bind address |
A11Y_MCP_STATELESS |
(unset) | Set to 1 for stateless mode |
GLOW_API_BASE_URL |
https://letitglow.app/mcp |
Endpoint 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:
{
"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:
claude mcp add --transport stdio a11y-agent-team -- node /path/to/mcp-server/dist/stdio.mjs
VS Code (.vscode/mcp.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/mcpby default. - You can call
glow_health_checkimmediately after starting this server.
Use a different GLOW endpoint
Option 1: set server environment variable before startup:
# Linux/macOS
export GLOW_API_BASE_URL="https://letitglow.app/mcp"
npm start
# 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_checkwithbaseUrlglow_audit_documentwithbaseUrlglow_fix_documentwithbaseUrlglow_convert_documentwithbaseUrlglow_generate_reportwithbaseUrl
Example prompts after connection
Run glow_health_checkAudit ./docs/sample.md with glow_audit_document using format markdownConvert ./docs/sample.md from markdown to html with glow_convert_documentGenerate 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:
- Install a Node.js LTS release (26, 24 or 22).
- Open this folder:
mcp-server/ - Run
npm install - Start the server with
npm start - Point your MCP client at
http://127.0.0.1:3100/mcp - Install the skills (see Getting started) if you want the guided PDF workflow in chat
Minimum files for the MCP side:
package.jsonserver.jsserver-core.jsstdio.jstools/
If you also want the chat workflow layer, add:
- the
pdf-accessibilityandpdf-scan-configskills (skills/pdf-accessibility/,skills/pdf-scan-config/), installed with the rest of the package templates/pdf-config-moderate.jsoncopied to your project as.a11y-pdf-config.json(optional)
Available Tools
Core Tools
Each tool, with its description.
| Tool | Description |
|---|---|
check_contrast |
Calculate WCAG contrast ratio between two colors |
get_accessibility_guidelines |
Get WCAG AA guidelines for component types |
check_heading_structure |
Analyze HTML heading hierarchy |
check_link_text |
Detect ambiguous or missing link text |
check_form_labels |
Check form inputs for accessible labels |
Document Tools
Each tool, with its description.
| Tool | Description |
|---|---|
scan_office_document |
Scan .docx/.xlsx/.pptx for accessibility issues |
scan_pdf_document |
Scan PDF using PDF/UA checks |
scan_epub_document |
Scan .epub files for EPUB Accessibility 1.1 conformance |
extract_document_metadata |
Extract accessibility-relevant metadata |
batch_scan_documents |
Scan multiple documents in one call |
fix_document_metadata |
Fix document metadata (title, language, author) |
fix_document_headings |
Fix heading structure in documents |
GLOW Bridge Tools
Each tool, with its description.
| Tool | Description |
|---|---|
glow_health_check |
Check health of a GLOW endpoint (default: https://letitglow.app/mcp) |
glow_audit_document |
Upload a markdown/html/docx file to GLOW and run /audit |
glow_fix_document |
Upload a markdown/html/docx file to GLOW and run /fix |
glow_convert_document |
Upload a markdown/html/docx file to GLOW and run /convert |
glow_generate_report |
Upload a markdown/html/docx file to GLOW and run /report |
Advanced Tools (Optional Dependencies)
Each tool, with its requires and description.
| Tool | Requires | Description |
|---|---|---|
run_axe_scan |
playwright, @axe-core/playwright | Run axe-core against a live URL |
run_playwright_a11y_tree |
playwright | Capture accessibility tree |
run_playwright_keyboard_scan |
playwright | Test keyboard navigation |
run_playwright_contrast_scan |
playwright | Visual contrast analysis |
run_playwright_viewport_scan |
playwright | Test reflow at multiple widths |
run_verapdf_scan |
veraPDF CLI | PDF/UA-1 (default), PDF/UA-2 or PDF/A validation, chosen with flavour (SARIF output) |
convert_pdf_form_to_html |
pdf-lib | Convert PDF forms to accessible HTML |
Markdown Tools
Each tool, with its description.
| Tool | Description |
|---|---|
scan_markdown_document |
Scan markdown files for accessibility issues (links, alt text, headings, tables, emoji) |
Caching Tools
Each tool, with its description.
| Tool | Description |
|---|---|
check_audit_cache |
Check if a cached audit result exists for a file |
update_audit_cache |
Store or update an audit result in the cache |
Installing Optional Dependencies
# Playwright + axe-core (for web scanning)
npm install playwright @axe-core/playwright
npx 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 --fixis part of the supported workflow here
Install veraPDF
veraPDF requires Java 11 or later.
Windows
Install Java first if it is not already present:
winget install --exact --id EclipseAdoptium.Temurin.21.JRE
Then install veraPDF using Chocolatey if available:
choco install verapdf
If Chocolatey is not part of your environment, use the manual installer from https://docs.verapdf.org/install/.
macOS
brew install verapdf
Manual download
Download from https://docs.verapdf.org/install/ and make sure verapdf is available on your PATH.
Verify veraPDF
verapdf --version
On Windows, restart your terminal or editor after installing Java or veraPDF so the updated PATH is picked up.
Use veraPDF directly
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 veraPDFValidate 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
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.
| Prompt | Arguments | Description |
|---|---|---|
audit-page |
url (required), level (optional: A/AA/AAA) |
Structured WCAG audit instruction; walks through axe-core, heading, link, form, keyboard, and contrast scans |
check-component |
component (required) |
Component-specific review using built-in guidelines (modal, tabs, accordion, combobox, carousel, form, live-region, navigation, general) |
explain-wcag |
criterion (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 URI | Description |
|---|---|
a11y://guidelines/{component} |
Component accessibility guidelines in Markdown (modal, tabs, accordion, combobox, carousel, form, live-region, navigation, general) |
a11y://tools |
Auto-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(notexec) with argument arrays - File size limits: Documents capped at 100 MB, batch operations at 50 files
- Local binding: Server binds to
127.0.0.1by default (not exposed to network)
Deployment
Docker
FROM node:24-slim
WORKDIR /app
COPY package.json .
RUN npm install
COPY . .
EXPOSE 3100
CMD ["node", "server.js"]
Systemd
[Unit]
Description=A11y Agent Team MCP Server
After=network.target
[Service]
Type=simple
ExecStart=/usr/bin/node /opt/a11y-mcp/server.js
Environment=PORT=3100
Restart=on-failure
[Install]
WantedBy=multi-user.target
License
MIT. See LICENSE in the repository root.
Accessibility Agents MCP questions
How do I add Accessibility Agents MCP to Claude Code?
Run claude mcp add accessibility-agents -- npx -y @community-access/accessibility-agents-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Accessibility Agents MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Accessibility Agents MCP provide?
It exposes 39 tools, including check_contrast, check_apca_contrast, get_accessibility_guidelines, check_heading_structure, check_link_text.
Does PDF scanning work without the MCP server installed?
No. The skills only provide scanning instructions; the actual scan_pdf_document tool comes from the MCP server.
How do I run the server without installing anything?
Run the bundled stdio entry point directly with Node, which needs no npm install.
Can I use it with Claude Desktop or VS Code?
Yes, it works with Claude Code, Claude Desktop, VS Code, the Copilot CLI and any MCP-compatible client over stdio or HTTP.
Is there an option for fast PDF validation?
Yes, if Java 11+ and the veraPDF CLI are installed you can run deep PDF/UA or PDF/A validation with the run_verapdf_scan tool.