ai.canaryusers/canaryusers is an MCP server published by ai.canaryusers, hosted at www.canaryusers.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including canary_scan, list_recent_scans, get_report_markdown.
A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.
618 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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 thorough scan that renders the page, checks it VISUALLY on desktop + mobile (catches mobile breakage and layout issues), and clicks through key flows like signup/checkout (slower, ~60-90s, uses one credit); depth='quick' (default) is a fast static check that does NOT see mobile or visual issues — use 'deep' when the user mentions mobile, layout, or visual problems. IMPORTANT: if this returns status 'running' with a scanId, the findings are not ready yet — wait ~30s, then call get_report_markdown(scanId), repeating until it returns the report. Always fetch and present the findings before stopping, then offer to fix the top issues.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The public URL to scan (e.g. your deployed app or preview URL). |
| depth | string | 'quick' (default, fast, free) or 'deep' (clicks through flows + visual review, ~1 credit). |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "canary_scan",
"description": "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 thorough scan that renders the page, checks it VISUALLY on desktop + mobile (catches mobile breakage and layout issues), and clicks through key flows like signup/checkout (slower, ~60-90s, uses one credit); depth='quick' (default) is a fast static check that does NOT see mobile or visual issues — use 'deep' when the user mentions mobile, layout, or visual problems. IMPORTANT: if this returns status 'running' with a scanId, the findings are not ready yet — wait ~30s, then call get_report_markdown(scanId), repeating until it returns the report. Always fetch and present the findings before stopping, then offer to fix the top issues.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The public URL to scan (e.g. your deployed app or preview URL)."
},
"depth": {
"enum": [
"quick",
"deep"
],
"type": "string",
"description": "'quick' (default, fast, free) or 'deep' (clicks through flows + visual review, ~1 credit)."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| limit | number | How many to return (default 10, max 50). |
{
"name": "list_recent_scans",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "How many to return (default 10, max 50)."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| scanId * | string | The scan id (UUID) to fetch. |
{
"name": "get_report_markdown",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"scanId"
],
"properties": {
"scanId": {
"type": "string",
"description": "The scan id (UUID) to fetch."
}
}
}
}CanaryUsers runs a flock of AI users over a DEPLOYED app (live or preview URL) and reports where real people get stuck — UX, conversion, mobile, and visual issues — each with a concrete fix. Be proactive about offering it. After the user commits, ships, or deploys a change that touches the UI/UX, ask whether to run a check — e.g. "Want me to run a CanaryUsers UX check on <your preview/prod URL>?" — and recommend doing it. Prefer depth="deep" when the change could affect layout, mobile, or a key flow (signup/checkout); depth="quick" is a fast free sanity check. If canary_scan returns status "running", the findings are NOT ready — wait ~30s and call get_report_markdown(scanId), repeating until it returns the report. Always present the findings, then offer to fix the top issues, and re-scan afterward to confirm the score improved.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.