[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Firecrawl web search](https://spiral.ai/integrations/gemini-cli/firecrawl-web-search)

# How to Use Firecrawl web search in Gemini CLI

Firecrawl web search returns ranked web, news, or image results, including titles and source links. Use it to discover relevant pages for research, news briefs, or documentation questions when you do not already know the URL.

|  |  |
| --- | --- |
| Model | Firecrawl web search |
| Available through | Firecrawl |
| Category | Web |
| Price | $0.00349 per 10 results. Scraping each result: $0.00175 ($0.00873 with JSON output). Each parsed PDF page: $0.00175. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Firecrawl web search in Gemini CLI

- Use Firecrawl web search to find official Next.js caching documentation relevant to the version in package.json. Return five source links and compare the returned passages with our caching code.
- Use Firecrawl web search to find official React documentation about useEffect cleanup. Compare the returned passages with effects in this project and propose fixes supported by those sources.
- Use Firecrawl web search to find PostgreSQL documentation about JSONB indexes. Read our migration files and produce a source-linked investigation plan for the JSON queries we use.
- Use Firecrawl web search to find Stripe documentation on webhook retries and duplicate events. Compare the returned guidance with our webhook handler and list the gaps to investigate.
- Use Firecrawl web search to find Playwright documentation on flaky test retries and auto-waiting. Compare the returned references with our test configuration and recommend specific changes.

## How to set up Firecrawl web search in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Firecrawl web search**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "firecrawl",
    "model": "firecrawl/search",
    "input": {
      "query": "<query>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Firecrawl web search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Firecrawl web search tools and prices

- [Firecrawl Search · Web Search](https://spiral.ai/tools/firecrawl/firecrawl/search) (Firecrawl): $0.00349 per 10 results. Scraping each result: $0.00175 ($0.00873 with JSON output). Each parsed PDF page: $0.00175.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| tbs |  | — | Time-based search parameter. Supports predefined time ranges (`qdr:h`, `qdr:d`, `qdr:w`, `qdr:m`, `qdr:y`), custom date ranges (`cdr:1,cd_min:MM/DD/YYYY,cd_max:MM/DD/YYYY`), and sort by date (`sbd:1`). Values can be combined, e.g. `sbd:1,qdr:w`. |
| safe |  | — | When `true`, filters explicit content from search results (SafeSearch). Omit to keep the default behavior, which does not apply the filter. |
| limit | 1 to 100 | 10 | Maximum number of results to return (per source type when using multiple sources) |
| country |  | US | ISO country code for geo-targeting search results (e.g. `US`). For best results, set both this and the `location` parameter. |
| sources |  | [{"type":"web"}] | Sources to search. Will determine the arrays available in the response. Defaults to ['web']. The plain string form (e.g. `["web", "alexandria"]`) is also accepted. The `alexandria` source returns tool contracts discovered from the Alexandria catalogue in `data.tools` instead of search results; it is free and is never counted in `creditsUsed`. Requires the team's Alexandria access to be enabled (403 otherwise). |
| timeout |  | 60000 | Timeout in milliseconds |

## What can you do with Firecrawl web search in Gemini CLI?

Build a source-linked fix plan by finding documentation relevant to the code in your project. Firecrawl returns titles, URLs, and descriptions that help the agent select references for a migration or bug investigation.

### Find documentation for a coding task

Search for Next.js caching documentation and return relevant page titles, links, and passages to compare with the project's implementation.

### Prepare a company news brief

Find coverage of NVIDIA announcements, then organize the returned titles, links, and descriptions into a reading list.

### Watch for product announcements

Repeat searches for Shopify product announcements and flag source URLs that were absent from earlier results.

### Build a research reading list

Find pages about sodium-ion batteries and group the returned sources into research, manufacturing, and deployment topics.

### Collect sources for a customer answer

Find official Stripe documentation relevant to a webhook question and prepare an answer with supporting links.

### Compare public product documentation

Search the public documentation of PostgreSQL and MySQL for JSON indexing, then assemble a source list for a technical comparison.

### Discover images for editorial research

Find image results for NASA's Artemis program and compile their titles and source links for review before selecting material.

## Overview

- [Firecrawl](https://spiral.ai/providers/firecrawl)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Firecrawl web search in other agents

- [Amp](https://spiral.ai/integrations/amp/firecrawl-web-search)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/firecrawl-web-search)
- [Claude](https://spiral.ai/integrations/claude-desktop/firecrawl-web-search)
- [Claude Code](https://spiral.ai/integrations/claude-code/firecrawl-web-search)
- [Cline](https://spiral.ai/integrations/cline/firecrawl-web-search)
- [Codex](https://spiral.ai/integrations/codex/firecrawl-web-search)
- [Cursor](https://spiral.ai/integrations/cursor/firecrawl-web-search)
- [Devin](https://spiral.ai/integrations/devin/firecrawl-web-search)
- [dots](https://spiral.ai/integrations/dots/firecrawl-web-search)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/firecrawl-web-search)
- [Gemini](https://spiral.ai/integrations/gemini/firecrawl-web-search)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/firecrawl-web-search)
- [goose](https://spiral.ai/integrations/goose/firecrawl-web-search)
- [Grok](https://spiral.ai/integrations/grok/firecrawl-web-search)
- [Grok Build](https://spiral.ai/integrations/grok-build/firecrawl-web-search)
- [Hermes](https://spiral.ai/integrations/hermes/firecrawl-web-search)
- [Instinct](https://spiral.ai/integrations/instinct/firecrawl-web-search)
- [Manus](https://spiral.ai/integrations/manus/firecrawl-web-search)
- [Muse](https://spiral.ai/integrations/muse/firecrawl-web-search)
- [Muse Code](https://spiral.ai/integrations/muse-code/firecrawl-web-search)
- [n8n](https://spiral.ai/integrations/n8n/firecrawl-web-search)
- [Notion](https://spiral.ai/integrations/notion/firecrawl-web-search)
- [OpenClaw](https://spiral.ai/integrations/openclaw/firecrawl-web-search)
- [opencode](https://spiral.ai/integrations/opencode/firecrawl-web-search)
- [Perplexity](https://spiral.ai/integrations/perplexity/firecrawl-web-search)
- [Raycast](https://spiral.ai/integrations/raycast/firecrawl-web-search)
- [VS Code](https://spiral.ai/integrations/vscode/firecrawl-web-search)
- [Windsurf](https://spiral.ai/integrations/windsurf/firecrawl-web-search)
- [Zapier](https://spiral.ai/integrations/zapier/firecrawl-web-search)

## More Gemini CLI guides

- [Firecrawl web research](https://spiral.ai/integrations/gemini-cli/firecrawl-web-research)
- [Firecrawl website URLs](https://spiral.ai/integrations/gemini-cli/firecrawl-website-urls)
- [Firecrawl web page content](https://spiral.ai/integrations/gemini-cli/firecrawl-web-page-content)
- [Firecrawl website content](https://spiral.ai/integrations/gemini-cli/firecrawl-website-content)
- [Firecrawl developer search](https://spiral.ai/integrations/gemini-cli/firecrawl-developer-search)
- [Google search results](https://spiral.ai/integrations/gemini-cli/google-search-results)

## Questions about Firecrawl web search in Gemini CLI

**Can Gemini CLI use Firecrawl web search?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Firecrawl web search like any built-in tool.

**How much does Firecrawl web search cost in Gemini CLI?**

$0.00349 per 10 results. Scraping each result: $0.00175 ($0.00873 with JSON output). Each parsed PDF page: $0.00175. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need a Firecrawl account to use Firecrawl web search in Gemini CLI?**

No. Spiral runs Firecrawl web search on its own Firecrawl account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Firecrawl web search in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Firecrawl web search runs?**

Firecrawl web search runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**What does a Firecrawl search result contain?**

Basic results include a title, URL, and description. Descriptions can contain query-relevant passages from the page when highlights are available.

**How many results can one search return?**

The maximum is 100 results per source type. Requesting 10 web results and 10 news results can return up to 20 results altogether.

**Can I restrict results to recent coverage?**

The Search feature documentation says date filtering applies to web results and does not filter news or images. For a dated news brief, use web results targeted to the news publications you want.

**Does Firecrawl find every relevant page?**

No. Firecrawl explicitly warns that search may miss sources or return unexpected results, so a result list cannot establish complete coverage of a topic.

**Does Firecrawl verify the accuracy of returned content?**

Firecrawl's terms disclaim responsibility for third-party content's accuracy and timeliness. Search results provide sources to assess, rather than a factual accuracy guarantee.

