Canaryusers

canaryusers-ai/canaryusers-mcp

Connects to the hosted CanaryUsers service and exposes three tools: canary_scan to run UX tests against a live URL (quick or deep mode), list_recent_scans to retrieve your scan history, and get_report_markdown to fetch full reports. The deep scan actually renders your page on desktop and mobile, clicks through flows like signup or checkout, and returns concrete findings about where users would bail. You'd use this right after deploying a UI change or before a launch to catch mobile breakage, confusing UX, or conversion dead ends that analytics won't surface. Quick scans are free. Deep scans use credits and take 60 to 90 seconds. Requires a token from canaryusers.ai. Remote only, nothing to host.

tools: 3
auth: Secret needed
transport: HTTP
last updated: Jun 13, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://www.canaryusers.ai/api/mcp --name canaryusers --header 'Authorization: Bearer ${API_TOKEN}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http canaryusers https://www.canaryusers.ai/api/mcp --header 'Authorization: YOUR_AUTHORIZATION'

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 3 tools

Verified live against the running server on Nov 6, 2026.

canary_scanRun a CanaryUsers UX scan on a DEPLOYED URL (your live or preview app — not source code). A flock of AI personas evaluates the page and reports where real users would get stuck, with concrete fixes. Returns AI-ready findings you can act on immediately. Use depth='deep' for the...2 params

Run a CanaryUsers UX scan on a DEPLOYED URL (your live or preview app — not source code). A flock of AI personas evaluates the page and reports where real users would get stuck, with concrete fixes. Returns AI-ready findings you can act on immediately. Use depth='deep' for the...

Parameters* required

depthstring

'quick' (default, fast, free) or 'deep' (clicks through flows + visual review, ~1 credit).one of quick · deep

url*string

The public URL to scan (e.g. your deployed app or preview URL).

list_recent_scansList the most recent CanaryUsers UX scans for your account (id, URL, CanaryScore, grade, status, date). Use this to find a scan to dig into.1 params

List the most recent CanaryUsers UX scans for your account (id, URL, CanaryScore, grade, status, date). Use this to find a scan to dig into.

Parameters* required

limitnumber

How many to return (default 10, max 50).

get_report_markdownGet one scan's full report as AI-ready markdown: the findings ranked by severity, why each matters, and how to fix it. Pass a scanId from list_recent_scans.1 params

Get one scan's full report as AI-ready markdown: the findings ranked by severity, why each matters, and how to fix it. Pass a scanId from list_recent_scans.

Parameters* required

scanId*string

The scan id (UUID) to fetch.

Readme

CanaryUsers — MCP Server

Give your AI coding assistant eyes for UX: a flock of AI users tests your deployed app and reports where real people would bail — each with a concrete fix.

CanaryUsers sends a flock of behaviorally‑diverse AI users through your deployed web app (a live or preview URL) and reports exactly where real people get stuck — confusing UX, broken mobile layouts, dead‑end conversion paths, and visual glitches — each with a concrete, AI‑ready fix you can apply in the same chat.

View the full README on GitHub

Details

Repository: github.com/canaryusers-ai/canaryusers-mcp
Website: www.canaryusers.ai/mcp
Transport: HTTP
Auth: Required
Registry: MCP registry, active
Tools verified: Nov 6, 2026