Search with Firecrawl

Firecrawl searches the live web and news. Pin a query to Firecrawl with one field, and its results come back in the same shape as every other provider’s.

Pinned to Firecrawl, answered in 2,194 ms.

Results from Firecrawl

1
S&P 500 (^GSPC) Charts, Data & News - Yahoo Finance finance.yahoo.com
2
SPX: S&P 500 Index - Stock Price, Quote and News - CNBC cnbc.com
3
.SPX - S&P 500 INDEX | Quotes from Fidelity Investments digital.fidelity.com
4
S&P 500 INDEX TODAY | INX LIVE TICKER - Markets Insider markets.businessinsider.com
5
US Markets, World Markets, and Stock Quotes | CNN cnn.com

Recorded from live searches on 9 October 2026.

Pin a query to Firecrawl

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

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": "S&P 500 today",
    "top_k": 5,
    "requested_provider": "firecrawl"
  }'

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": "S&P 500 today",
        "top_k": 5,
        "requested_provider": "firecrawl",
    },
    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: "S&P 500 today",
    top_k: 5,
    requested_provider: "firecrawl",
  }),
})

const { results } = await res.json()

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

Filters Firecrawl 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.

request.jsonJSON

{
  "query": "S&P 500 today",
  "top_k": 5,
  "requested_provider": "firecrawl",
  "filters": {
    "domains": { "values": ["finance.yahoo.com"] }
  }
}