A11Y Toolkit MCP Server

by kinti Your server? Claim it

local only

A11Y Toolkit runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 16 Sep 2026.

The accessibility layer for AI coding agents: audit, fix, document and watch - WCAG 2.2.

—

Installs / week

pypi · a11y-toolkit

Stars

0 open issues

16 Sep 2026

Last commit

no recent releases

MIT

License

Python

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command contrast.py:302, [пакет] contrast.py:302

        subprocess.run(['sips', '-s', 'format', 'ppm', ruta, '--out', tmp],

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add a11y-toolkit -- uvx a11y-toolkit

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "a11y-toolkit": {
      "args": [
        "a11y-toolkit"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.a11y-toolkit]
command = "uvx"
args = ["a11y-toolkit"]

.cursor/mcp.json

{
  "mcpServers": {
    "a11y-toolkit": {
      "args": [
        "a11y-toolkit"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "a11y-toolkit": {
      "args": [
        "a11y-toolkit"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to A11Y Toolkit

same job, measured the same way

MCP Documentation Server

by andrea9293

Local-first document management and semantic search for AI coding agents

98 installs/wk local only

Docweave MCP

by nicolasmartalog

Generate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.

46 installs/wk 2 tools answering

markitai

by ynewtime

Convert documents, images and web pages to clean Markdown, for agents: single, URL and batch tools.

local only

Outline MCP Server

by vortiago

Connect AI assistants to Outline for document search, reading, and management

482 installs/wk local only

AlloFlow Document Remediation

by apomera

Local-first document accessibility remediation using the canonical AlloFlow app pipeline.

local only

Groupdocs Watermark MCP

by groupdocs-watermark

MCP server for GroupDocs.Watermark — add and search document watermarks via AI agents.

local only

Unmarkdown

by unmarkdown

The document publishing layer for AI tools. Convert markdown to 6 destinations, 62 templates.

37 installs/wk answering

Superdocs

by superdocs

AI document editing for agents: draft, edit, export .docx/PDF. 37 MCP tools; agent self-signup.

answering

A11Y Toolkit — questions

Answers built from our own checks of this server.

Why is there no uptime for A11Y Toolkit?

A11Y Toolkit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package a11y-toolkit.

How do I connect A11Y Toolkit?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls a11y-toolkit straight from pypi; nothing to host, nothing to sign up for.

Is A11Y Toolkit open source?

Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.