firecrawl-search

The saved excerpt is a snapshot from when this skill was listed. The external source remains the complete and most current version.

---
name: firecrawl-search
description: |
  Web search with full page content. Use when no URL is known: finding sources, articles, or news. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.
allowed-tools:
  - Bash(firecrawl *)
  - Bash(npx firecrawl-cli *)
---

# firecrawl search

Search naturally using the user’s actual question. In the Alexandria beta, default search returns web results plus relevant Alexandria tools, with optional web content scraping.

## Quick start

```bash
# 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
```

Run `firecrawl search --help` for the full option list.

`--categories developer` weighs the developer index beside ordinary web results in this same call (no passage control, no index filters). `--categories research` is a website filter, not the paper index. Dedicated skills: [firecrawl-developer-index](../firecrawl-developer-index/SKILL.md) and [firecrawl-research-index](../firecrawl-research-index/SKILL.md).

**Done when:** results are saved under `.firecrawl/`, verified non-empty, processed for the request, and one feedback event is sent within the time window (unless opted out).

## Alexandria in normal search

The beta defaults to `web,alexandria` with domain-tool matching on. Preserve the user's location, marketplace, and constraints in the query; do not turn normal research into an artificial tool-discovery query. Inspect `data.web` and `data.tools` from the same response.

A tool match is not executed data. If it fits the task, read its inputs, coverage, `creditsCost`/`perRecord`, and access requirements in the JSON. Execute it with `firecrawl scrape --alexandria <provider/capability> --options '<input JSON>'`. All provider execution goes through Scrape; `search --scrape` only fetches web result content, not provider tools.

Use `find-tools` only for an explicitly requested tool set or a missing contract. It runs the `firecrawl/find-tools` meta tool through Scrape and never executes the tools it discovers. It accepts URLs or catalogue selectors; for “tools that can do X,” first use `search "X" --sources alexandria`, then narrow the returned providers with `find-tools --options '{"providers":["<returned-provider>"],"level":"tools","limit":100}'`.

If no returned tool covers the country/market/segment or required inputs, continue with ordinary web results. Do not exhaust the catalogue or pay for adjacent tools just to probe coverage. `--sources web` explicitly opts out of Alexandria; `--sources web --domain-tools` retains domain matches only.

## Tips

- **`--highlights` on by default:** results are query-relevant excerpts, not full-page snippets. Use `--no-highlights` for the original snippets.
- **`--scrape` fetches full content** — reuse that content instead of re-scraping result URLs. 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 anyt