Search with Ozone

Ozone searches real-time licensed publisher content, and every result it returns is marked licensed. Pin a query to Ozone with one field, and its results come back in the same shape as every other provider’s.

Pinned to Ozone, answered in 2,236 ms.

Results from Ozone

1
Archaeologists find more graves at lost Williamsburg African American cemetery washingtonpost.com
2
Metal detectorist finds ‘quite extraordinary’ second Bronze Age hoard in Scottish Borders independent.co.uk
3
Lightning DOES strike twice! Scottish detectorist finds second Bronze Age hoard scottishdailyexpress.co.uk
4
2,000-Year-Old Ring Engraved with a Lost Wonder of the Ancient World Unearthed from Underwater Resting Place people.com
5
Metal detectorist unearths two Bronze Age hoards in two years independent.co.uk

Recorded from live searches on 8 October 2026.

Pin a query to Ozone

Over HTTP, send "requested_provider": "ozone" with the query.
In an agent connected over MCP, ask it to search with Ozone.

Results come back in the same shape for every provider, as the docs describe. Leave the field out, and Grounder routes each query to the provider most likely to answer it well.

search.shShell

curl https://api.grounder.net/v1/search \
  -H "Authorization: Bearer $GROUNDER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "new archaeological finds announced this week",
    "top_k": 5,
    "requested_provider": "ozone"
  }'

import os
import httpx

KEY = os.environ["GROUNDER_KEY"]

r = httpx.post(
    "https://api.grounder.net/v1/search",
    headers={"Authorization": f"Bearer {KEY}"},
    json={
        "query": "new archaeological finds announced this week",
        "top_k": 5,
        "requested_provider": "ozone",
    },
    timeout=30,
).json()

for hit in r["results"]:
    print(hit["rank"], hit["title"], hit["url"])

const res = await fetch("https://api.grounder.net/v1/search", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.GROUNDER_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    query: "new archaeological finds announced this week",
    top_k: 5,
    requested_provider: "ozone",
  }),
})

const { results } = await res.json()

claude mcp add --transport http grounder \
  https://api.grounder.net/mcp
# then /mcp, grounder, Authenticate

Filters Ozone applies

Set them under filters. A filter a provider can’t apply returns 400 unsupported_filter.

Filter	Keeps
`domains`	Only these sites, or with `"mode": "exclude"`, none of them.
`recency`	The last so many days, or a `range` of dates.
`language`	One language, by its code.
`publisher_ids`	Only these Ozone publishers.
`article_types`	Only these kinds of Ozone article.
`temporal_sensitivity`	Only Ozone articles with these temporal sensitivity values.

request.jsonJSON

{
  "query": "new archaeological finds announced this week",
  "top_k": 5,
  "requested_provider": "ozone",
  "filters": {
    "domains": { "values": ["washingtonpost.com"] }
  }
}