firecrawl search

Web search with optional content scraping. Returns search results as JSON, optionally with full page content.

When to use

• You don't have a specific URL yet
• You need to find pages, answer questions, or discover sources
• First step in the workflow escalation pattern: search → scrape → map → crawl → interact

Quick start

# Basic search
firecrawl search "your query" -o .firecrawl/result.json --json

# Search and scrape full page content from results
firecrawl search "your query" --scrape -o .firecrawl/scraped.json --json

# News from the past day
firecrawl search "your query" --sources news --tbs qdr:d -o .firecrawl/news.json --json

# Programming question: search GitHub issues, merged PRs, READMEs, and docs
firecrawl search "your query" --categories developer -o .firecrawl/developer.json --json

Developer search

--categories developer adds an index built for coding agents. It covers GitHub issues, merged pull requests, repository READMEs, and curated documentation sites. Use it for a programming question: an error message, an API contract, a library behaviour, or a known bug.

The hits arrive in their own data.developer group beside data.web. Each hit holds url, title, and description, where description is the matched passage. Read the passages with jq -r '.data.developer[] | .url, .description' .firecrawl/developer.json.

The dedicated firecrawl developer command searches only that index and keeps the full matched passages:

# Developer search only, with full passages
firecrawl developer "your query" --limit 10 -o .firecrawl/developer.json --json

Each result holds id, type (issue, pull_request, readme, doc), url, title, and passages. Read them with jq -r '.results[] | .url, .passages[].text' .firecrawl/developer.json.

Options

Tips

• --scrape fetches full content — don't re-scrape URLs from search results. This saves credits and avoids redundant fetches.
• Always write results to .firecrawl/ with -o to avoid context window bloat.
• Use jq to extract URLs or titles: jq -r '.data.web[].url' .firecrawl/search.json
• Naming convention: .firecrawl/search-{query}.json or .firecrawl/search-{query}-scraped.json

Send feedback after every search (refunds 1 credit)

Search costs 2 credits. After you've actually used the results (or decided they were useless), send structured feedback with firecrawl search-feedback <id>. The first feedback per search refunds 1 credit and helps us improve search quality. Do this once per search, in the background, after you finish processing the results — it does not block your main task.

Opt out: if FIRECRAWL_NO_SEARCH_FEEDBACK=1 (or FIRECRAWL_DISABLE_SEARCH_FEEDBACK=1) is set, the CLI silently skips the call and never sends anything. Respect that — do not try to work around it. (Team admins can also disable this server-side; the API will return feedbackErrorCode: "TEAM_OPTED_OUT" and the CLI will exit 0 silently.)

Rules to know before you call this:

• Time window: must be sent within ~2 minutes of the search. Late feedback is rejected.
• --missing-content is the most important field. It's a list of specific pieces of content you expected but did not find. One topic per entry — do not pack multiple topics into one string. These aggregate across teams and tell us what to index next.
• Substantive content required (zero-effort feedback is rejected with HTTP 400):
  • good → must include at least one --valuable-sources entry.
  • partial → must include --valuable-sources or --missing-content.
  • bad → must include --missing-content or --query-suggestions.
• Daily refund cap (per team, per UTC day, default 100 credits). Once your team has been refunded 100 credits today, further submissions still record feedback but no longer refund credits. The response includes creditsRefundedToday / dailyRefundCap / dailyCapReached. When dailyCapReached: true, stop calling search-feedback for the rest of the UTC day — it won't refund anything and you're wasting bandwidth.
• Idempotent: re-submitting for the same search id returns success but no extra refund.
• --silent & is the right pattern — exit code 0 even on failure, so a rejected/expired call never crashes your pipeline.

Read the search response's id:

SEARCH_ID=$(jq -r '.id' .firecrawl/search-react-hooks.json)

Then send feedback. Pick the rating that matches what actually happened:

# Results were useful, with notes on what was still missing
firecrawl search-feedback "$SEARCH_ID" \
  --rating good \
  --valuable-sources '[{"url":"https://react.dev/reference/react/hooks","reason":"Most authoritative"}]' \
  --missing-content '[
    {"topic":"useDeferredValue","description":"No example of useDeferredValue with Suspense"},
    {"topic":"useTransition","description":"No coverage of useTransition for routing"}
  ]' \
  --query-suggestions "Boost react.dev for queries about react hooks" \
  --silent &

# Results were partially useful — multiple missing topics, one entry per topic
firecrawl search-feedback "$SEARCH_ID" \
  --rating partial \
  --missing-content '[
    {"topic":"useDeferredValue"},
    {"topic":"useTransition","description":"Need React 18+ examples"},
    {"topic":"Server Components hooks"}
  ]' \
  --silent &

# Quick form — repeat --missing-content or use comma-separated topics
firecrawl search-feedback "$SEARCH_ID" \
  --rating bad \
  --missing-content "official api reference: missing v2 endpoints" \
  --missing-content "code examples in python" \
  --silent &

--missing-content accepts:

• JSON array of {topic, description?} objects (richest, preferred)
• "topic: description" strings (shorthand)
• Plain "topic1, topic2, topic3" (when you only have topic names)
• Repeated --missing-content flags

--silent suppresses output and & runs it in the background so feedback never blocks you.

See also

• firecrawl-scrape — scrape a specific URL
• firecrawl-map — discover URLs within a site
• firecrawl-crawl — bulk extract from a site