Aether WCAG Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 23 Sep 2026.
WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.
We read the source, 2 h ago · rules 3dff92dd89df
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.
const child = spawn(process.execPath, [playwrightCli(), 'install', 'chromium'], {
const buf = await fs.readFile(path.join(outputDir, rel));
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 mcp add aether-wcag-scanner -- npx -y @allchemylabs/aether-wcag-scanner
{
"mcpServers": {
"aether-wcag-scanner": {
"args": [
"-y",
"@allchemylabs/aether-wcag-scanner"
],
"command": "npx"
}
}
}
[mcp_servers.aether-wcag-scanner]
command = "npx"
args = ["-y", "@allchemylabs/aether-wcag-scanner"]
{
"mcpServers": {
"aether-wcag-scanner": {
"args": [
"-y",
"@allchemylabs/aether-wcag-scanner"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"aether-wcag-scanner": {
"args": [
"-y",
"@allchemylabs/aether-wcag-scanner"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ALLCHEMY_API_KEY (Beta API key from https://beta.allchemylabs.ai (optional: without it the scanner runs fully offline with template fixes)).
The author declared them in the registry entry; get the values from the project itself.
MCP server for automated web accessibility scanning with Playwright and Axe-core.
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
Browser MCP: drive a real Chromium via Playwright with compact ref-addressable page snapshots
Local Playwright browser through residential proxies — agent picks country + sticky identity
MCP server that gives AI agents dynamic network chaos control over Playwright browser sessions
Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser.
Source-grounded web research: search, extraction, verification, and browser automation.
Answers built from our own checks of this server.