[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Firecrawl government documents](https://spiral.ai/integrations/codex/firecrawl-government-documents)

# How to Use Firecrawl government documents in Codex

Find ranked US statutes, regulations, codes, court opinions, and agency publications with titles, URLs, and matched excerpts. Use it to locate sources for a legal or regulatory question, then check the underlying document's status and version.

|  |  |
| --- | --- |
| Model | Firecrawl government documents |
| Available through | Firecrawl |
| Category | Data |
| Price | $0.013 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Firecrawl government documents in Codex

- Use Firecrawl government documents to find federal food allergen labeling sources and add a linked reading list to this project's research notes.
- Use Firecrawl government documents to find California consumer privacy notice sources and compare the returned excerpts with this project's privacy-policy draft.
- Use Firecrawl government documents to find Seattle accessory dwelling unit code sources and build a source-list view in this project.
- Use Firecrawl government documents to find federal appellate opinions citing 42 U.S.C. § 1983 and create a bibliography with returned titles and URLs.
- Use Firecrawl government documents to find EPA greenhouse gas reporting sources and add a research appendix to this project's documentation.

## How to set up Firecrawl government documents in Codex

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

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex 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 government documents**: 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/gov-search",
    "input": {
      "query": "<query>"
    }
  }'
```

Then paste one of the prompts above: Codex finds Firecrawl government documents on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## Firecrawl government documents tools and prices

- [Firecrawl Government · Search](https://spiral.ai/tools/firecrawl/firecrawl/gov-search) (Firecrawl): $0.013 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| k | 1 to 100 | 10 | Number of results to return. |
| cites |  | — | Keep only pages that cite a law or case, as a printed citation such as `42 U.S.C. § 1983` or `5 U.S. 137`, or a citation id such as `us:usc:42:1983`. Pass up to 32 to keep pages citing any of them. |
| court |  | — | Keep only pages labeled for one court, by CourtListener court id, such as `scotus`, `ca9` or `nysd`. |
| domain |  | — | Keep only pages from one site, such as `irs.gov`. |
| sources |  | ["web"] | Result groups to return, as one name or a list. `web` returns plain search results. `gov` returns the same results with the index's labels: `jurisdiction`, `court`, `courtType`, `cites`, `citedAs`, `lang` and `updatedAt`. |
| courtType | federal-supreme, federal-appellate, federal-district, federal-bankruptcy, federal-special, military, state-supreme, state-appellate, state-trial, state-special, state-attorney-general | — | Keep only pages from one type of court: `federal-supreme`, `federal-appellate`, `federal-district`, `federal-bankruptcy`, `federal-special`, `military`, `state-supreme`, `state-appellate`, `state-trial`, `state-special`, `state-attorney-general`. |

## What can you do with Firecrawl government documents in Codex?

Add linked US legal sources to a project's policy notes or research interface. A coding agent can organize Firecrawl's ranked titles, URLs, and excerpts into a reviewable source list.

### Find the regulation behind a requirement

Locate US food-labeling regulations and agency publications for an allergen-labeling research brief.

### Build a state-law source list

Collect California and Colorado privacy statutes into separate reading lists with titles, excerpts, and source links.

### Discover opinions interpreting a statute

Find federal court opinions citing 42 U.S.C. § 1983 for a legal research bibliography.

### Prepare a local-code reading list

Find Seattle code provisions relevant to accessory dwelling units and collect the returned document links for review.

### Check sources behind a policy claim

Search for statutes, regulations, and agency guidance behind a claim about US emissions reporting, then inspect the underlying texts.

### Maintain an agency-publication watchlist

Repeat focused EPA searches and flag newly appearing URLs for review without treating a ranking change as a legal change.

## Overview

- [Firecrawl](https://spiral.ai/providers/firecrawl)
- [All Codex guides](https://spiral.ai/integrations/codex)

## Firecrawl government documents in other agents

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

## More Codex guides

- [Bria editable ad layers](https://spiral.ai/integrations/codex/bria-editable-ad-layers)
- [Firecrawl paper search](https://spiral.ai/integrations/codex/firecrawl-paper-search)
- [Bria Fibo structured image prompt](https://spiral.ai/integrations/codex/bria-fibo-structured-image-prompt)
- [Firecrawl related research papers](https://spiral.ai/integrations/codex/firecrawl-related-research-papers)
- [Bria Fibo structured edit instructions](https://spiral.ai/integrations/codex/bria-fibo-structured-edit-instructions)
- [Firecrawl research paper metadata and passages](https://spiral.ai/integrations/codex/firecrawl-research-paper-metadata-and-passages)

## Questions about Firecrawl government documents in Codex

**Can Codex use Firecrawl government documents?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Firecrawl government documents like any built-in tool.

**How much does Firecrawl government documents cost in Codex?**

$0.013 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need a Firecrawl account to use Firecrawl government documents in Codex?**

No. Spiral runs Firecrawl government documents 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 government documents in Codex?**

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

**Does Codex wait while Firecrawl government documents runs?**

Firecrawl government documents runs in the background. Codex starts the run, checks on it and gives you the json when it's ready.

**Which jurisdictions and documents does Firecrawl cover?**

The Government Index focuses on US federal, state, and local material. It searches statutes, regulations, codes, court opinions, and other government publications.

**Does a result contain the full legal document?**

Results provide matched excerpts with a title, URL, description, and rank. Read the linked document when the excerpt does not establish the rule.

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

Each search returns up to 100 ranked results, with 10 as the default. That result cap does not establish how many relevant documents exist.

**Are all matches current, enacted law?**

Matches can include bills, historical versions, agency guidance, and third-party reproductions. Verify the issuer, jurisdiction, effective status, and version before citing a match as current governing law.

**Can a filtered search miss relevant documents?**

Yes. Filters retain pages with matching index labels, so relevant unlabeled pages can disappear from the results; court labels are most complete for federal courts and case-law collections.

