Google Discover automation · runs daily
Check if your site appears in Google Discover
You published a story that should suit Discover, and the Search Console report only shows a total for yesterday. You want to know whether a card from your domain is in the feed right now, and where.
Cotlet does it in your own Google Discover account with check_domain_in_feed and get_story_cluster, called by your AI agent, an n8n workflow or a script.
Hosted · nothing to install or maintain
Can Google Discover do this on its own?
Google offers no way to read the feed from code (checked 20 Oct 2026). The Discover report in Search Console shows impressions, clicks and CTR for content that appeared in Discover in the last 16 months, once the data reaches a minimum threshold of impressions. It does not say whether a story is in a given account's feed now, or at which position.
How you do it in Google Discover today
- Open the Google app, or google.com in a phone browser, signed in to the Google Account whose feed you want to check.
- Scroll the Discover feed and read the publisher name on each card, looking for your own.
- Tap More at the bottom right of a card to see Not interested in the topic or Don't show content from the source, which tells you which topic Discover filed the card under.
- Repeat on another day, because the feed changes through the day and between accounts. Nothing records what you saw, so the position and age of a card are lost the moment you scroll.
How to check if your site appears in Google Discover
Scan the top 40 cards of my Google Discover feed and tell me whether example-news.com appears. List the position, title, age and topic of each match. - 01
Scan the top of the feed
Your agent calls check_domain_in_feed with your domain and the number of cards to scan. The tool opens the feed of the signed-in account in your Cloud Browser, so the answer holds for that account and the country of that Cloud Browser, not for everyone.
- 02
Treat a miss as a miss for this feed
No match means the domain was not in the scanned cards of this account at this moment. The agent says so and does not claim your story is absent from Discover. Eligibility is not a guarantee of appearing, and Discover traffic is less predictable than keyword search.
- 03
Open the cluster of each match
For every match, get_story_cluster returns the more stories from the same event. The agent reads which other publishers sit next to your card and whether yours is the lead.
- 04
Report the position and the topic
The agent writes one line per match with position, title, age and topic, and compares the position with the previous run if your prompt includes it. A card that disappears between two runs is reported as dropped from the scan, not as removed.
What you get back
example-news.com in my Discover feed (US), top 40 cards scanned:
Position 3: "Ten herbs that survive a cold windowsill", 3h, topic Home gardening
Position 11: "How to feed a sourdough starter", 1d, topic Sourdough baking
Position 11 shares a cluster with 4 other publishers; yours is not the lead. Other ways to ask
- Every morning at 8, scan 60 cards in the US and UK Cloud Browsers and tell me which feed shows example-news.com.
- Check three domains, mine and two I follow, and list who has more cards in my top 40.
- Tell me only when my domain was in the feed yesterday and is not today.
What Google Discover allows, and what to know first
- Discover recommends content based on a person's Web and App Activity, so two accounts see different feeds.
- Content is eligible automatically when it is indexed and follows the Discover content policies; no special tags or structured data are required, and eligibility is not a guarantee.
- Older content can appear in Discover if it is helpful and relevant to a person's interests.
- Some Discover features are not available in all languages and countries, so the feed depends on the country of your Cloud Browser.
Every tool here only reads, so it can run daily from n8n, Make, Zapier or cron without waiting for your OK.
Sources: Search Central: Google Discover · Google Search Help: Customize what you find in Discover
Call check_domain_in_feed from a script
curl "https://cotlet.dev/api/v1/google-discover/domain-in-feeds/check?domain=example-news.com&limit=40" \
-H "Authorization: Bearer $COTLET_API_KEY" {
"domain": "example-news.com",
"in_feed": true,
"cards_scanned": 40,
"matches": [
{
"position": 3,
"title": "Ten herbs that survive a cold windowsill",
"url": "https://example-news.com/guides/windowsill-herbs",
"age": "3h",
"topic": "Home gardening"
},
{
"position": 11,
"title": "How to feed a sourdough starter",
"url": "https://example-news.com/guides/sourdough-starter",
"age": "1d",
"topic": "Sourdough baking"
}
]
} MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is google_discover_read → check_domain_in_feed. Example data.
Schedule it in n8n, Make, Zapier or cronGoogle Discover tools this automation uses
| Tool | Parameters |
|---|---|
| check_domain_in_feed | domain, limit |
| get_story_cluster | url |
Frequently asked questions
Is it safe to connect Google Discover to Cotlet?
Yes. You sign in to Google Discover yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Google Discover once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.
Give your agent access to Google Discover.
Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with Google Discover.