Pandus Accessibility

npx add-mcp 'https://pandus.online/mcp'

AI assistants already write a large part of the code of many sites. The Pandus MCP server gives them what they lack for accessibility: what is actually wrong on your pages, why it matters for your customers and how to fix it on your platform. The assistant reads the problem, finds the template that renders it in your project, fixes the cause and starts a new check to confirm it.

It works with any assistant that supports remote MCP servers, not with one vendor. Results come from an automated check, not a full audit, and not legal advice.

What the assistant can do

Tool	What it does	Needs
search_rules	Finds rule cards by words, an axe-core rule id or a WCAG criterion	nothing
explain_rule	One rule: what is wrong, who is affected, how to fix it in code and on Shopify, WooCommerce, PrestaShop, Shoptet	nothing
explain_wcag_criterion	A WCAG 2.2 level A or AA criterion in plain words, with manual tests	nothing
list_sites	Your sites with the latest check and problems by severity	sign-in or token
what_to_fix	Open problems of a site, most important first, from the scanner, real visitors, the extension and reports	sign-in or token
get_problem	One problem: pages, CSS selectors, HTML examples, the fix for your platform, WCAG clauses	sign-in or token
get_report	The latest check: problem types, pages, trend	sign-in or token
compare_checks	What was fixed, what is new and what is still open between the two latest checks	sign-in or token
start_check	Starts a new check of the site within your plan	allowed at sign-in, or a token with write
check_status	The progress of a check	sign-in or token

Two ready prompts come with it: fix the most important problems of a site in your codebase, and write an update for the site owner in their language.

Connect your AI assistant

There are two ways to let an assistant see your own sites. Signing in from the assistant (OAuth) is the simple one: Claude, ChatGPT, Perplexity, Claude Code, Cursor and VS Code open a Pandus page on first use, you choose the team the assistant sees and whether it may start checks, nothing is copied by hand. An API token is for clients without a sign-in, such as Gemini CLI: create it in Pandus under AI assistants and API and send it as Authorization: Bearer YOUR_TOKEN. Without either, the server still answers the free rule reference.

Connect your assistant in two minutes

Every assistant needs the same thing: the address of the Pandus server. Copy it here, then follow the steps for your assistant.

Server address

https://pandus.online/mcp

Without signing in it explains any accessibility rule for free. Sign in from the assistant to see your own sites (Pro and Agency plans).

Your assistant

Claude

1. Open Claude on the web or in the desktop app and go to Settings → Connectors. Open the connectors page
2. Press Add custom connector. Name: Pandus. URL: the address above. Save. https://pandus.online/mcp Copy
3. The first time you use a Pandus tool, the assistant opens the Pandus sign-in page: choose the team it may see, allow new checks if you want, and press Allow.

ChatGPT

1. ChatGPT (paid plans): open Settings → Apps and connectors → Advanced settings and turn on Developer mode.
2. Press Create. Name: Pandus. MCP server URL: the address above. Authentication: OAuth. Create. https://pandus.online/mcp Copy
3. The first time you use a Pandus tool, the assistant opens the Pandus sign-in page: choose the team it may see, allow new checks if you want, and press Allow.
4. In Business and Enterprise workspaces an admin may need to allow custom connectors first.

Claude Code

1. Run this in a terminal: claude mcp add --transport http pandus https://pandus.online/mcp Copy
2. Ask Claude Code something about Pandus, for example “what should I fix on shop.example?”. It opens the Pandus sign-in in your browser: choose the team and press Allow.

Cursor

1. Add to Cursor Cursor opens and asks you to confirm the server.
2. Or add this by hand to ~/.cursor/mcp.json (or.cursor/mcp.json in the project):

   {
       "mcpServers": {
           "pandus": {
               "url": "https://pandus.online/mcp"
           }
       }
   }
   

   Copy
3. The first time you use a Pandus tool, the assistant opens the Pandus sign-in page: choose the team it may see, allow new checks if you want, and press Allow.

VS Code

1. Install in VS Code VS Code opens and asks you to confirm the server.
2. Or add this by hand to.vscode/mcp.json in the project:

   {
       "servers": {
           "pandus": {
               "type": "http",
               "url": "https://pandus.online/mcp"
           }
       }
   }
   

   Copy
3. The first time you use a Pandus tool, the assistant opens the Pandus sign-in page: choose the team it may see, allow new checks if you want, and press Allow.

Gemini CLI

1. Gemini CLI has no sign-in: create an API token in Pandus under AI assistants and API (a read-only token is enough). Create a token
2. Run this in a terminal, with your token instead of YOUR_TOKEN: gemini mcp add --transport http pandus https://pandus.online/mcp --header "Authorization: Bearer YOUR_TOKEN" Copy

Perplexity

1. Perplexity (Pro, Max, Enterprise): open Settings → Connectors and press Add connector.
2. Choose a custom connector. Name: Pandus. Server URL: the address above. Save. https://pandus.online/mcp Copy
3. The first time you use a Pandus tool, the assistant opens the Pandus sign-in page: choose the team it may see, allow new checks if you want, and press Allow.

Other assistants

1. Windsurf, Cline and other clients that connect to remote servers take the address above; they sign in through OAuth where they support it, otherwise they take an API token in the header Authorization: Bearer YOUR_TOKEN.
2. Clients that only start local servers can run our small open-source proxy with an API token:

   {
       "mcpServers": {
           "pandus": {
               "command": "npx",
               "args": [
                   "-y",
                   "@pandus/mcp"
               ],
               "env": {
                   "PANDUS_API_TOKEN": "YOUR_TOKEN"
               }
           }
       }
   }
   

   Copy

Connected assistants are listed in Pandus under AI assistants and API, where one click disconnects them. Keep tokens out of shared repositories.

What to ask

• "Use Pandus: what are the three most important accessibility problems on shop.example, and where are they in this repository?"
• "Fix the image-alt problem Pandus found on the product pages, then start a new check."
• "Explain WCAG 2.4.7 and check our button styles for it."
• "Compare the last two Pandus checks and write a short update for the client in German."

Pandus and open-source axe MCP servers

What you need	Pandus MCP server	Open-source axe MCP servers
Check one page now	Weekly checks of the whole site, plus a check on demand	Yes, from your computer
What to fix first	Ranked by impact on customers, pages and real visitors	A list of axe results
Barriers real visitors met	Yes, with the Pandus SDK, as totals	No
Fix for Shopify, WooCommerce and code	Yes, in 7 languages	axe-core help texts
Before and after	Comparison of two checks	You compare by hand
Pages behind a login, localhost	With the browser extension	Yes

Both kinds can run side by side: an open-source server for local tests while you develop, Pandus for the whole site and the team.

Security and data

• Only your team's data. A sign-in or a token sees the sites of one team, as in the API, and stops working when the plan no longer includes the API or when you disconnect the assistant.
• Untrusted HTML. Code snippets from your pages are shortened and marked as untrusted, so text hidden in a page cannot give the assistant orders.
• No visitor data. Barriers real visitors met come as totals; session recordings are never sent.
• Limits and history. Requests are limited per token, and every call over your data is written to your team's activity log.

Plans

The rule reference is free for everyone. Your sites, "what to fix", reports and new checks over MCP come with the Pro and Agency plans, the same plans that include the API. See pricing.