[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Firecrawl developer search](https://spiral.ai/integrations/chatgpt/firecrawl-developer-search)

# How to Use Firecrawl developer search in ChatGPT

Firecrawl developer search returns ranked passages from public repository issues, merged pull requests, READMEs, and curated docs. Use it to investigate an error or check an API contract with source evidence.

|  |  |
| --- | --- |
| Model | Firecrawl developer search |
| Available through | Firecrawl |
| Category | Web |
| Price | $0.003492 per 10 results. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Firecrawl developer search in ChatGPT

- Use Firecrawl developer search to explain React's 'Hydration failed' error using facebook/react issues and documentation. Show the passages that support each explanation.
- Use Firecrawl developer search to find documentation explaining Pydantic 2's model_validate behavior. Summarize what it accepts and link the supporting passages.
- Use Firecrawl developer search to investigate redirect loops involving middleware in vercel/next.js. Separate reported symptoms from changes described in merged pull requests.
- Use Firecrawl developer search to find SQLAlchemy documentation and issues about MissingGreenlet with AsyncSession. Explain the conditions described in the returned passages.
- Use Firecrawl developer search to find urllib3 documentation about retries after HTTP 429 responses. Explain the documented behavior with source links.

## How to set up Firecrawl developer search in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 developer 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/developer-search",
    "input": {
      "query": "<query>"
    }
  }'
```

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

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

## Firecrawl developer search tools and prices

- [Firecrawl Developer Search · Code and Docs](https://spiral.ai/tools/firecrawl/firecrawl/developer-search) (Firecrawl): $0.003492 per 10 results.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| k | 1 to 100 | 10 |  |
| fork |  | — | Include or exclude forks. Applies to repository results only; sending it with no `sources` scope returns no `doc` results. |
| repos |  | — | Repository slugs to scope the repository half of the index to. Applies to the `issue`, `pull_request`, and `readme` types only. Sent together with `sources`, the two halves are combined rather than intersected. Returns 400 when no repository type is in `types`, reporting that `repos` cannot match any requested type and that you should add repository types or drop `repos`. |
| topic |  | — | Repository topic, such as `async`. Applies to repository results only; sending it with no `sources` scope returns no `doc` results. |
| types |  | — |  |
| skills | only | — | Set to `only` to limit the search to indexed agent-skill files. |

## What can you do with Firecrawl developer search in ChatGPT?

Explain a library error with passages the reader can check against the original source. A chat app can compare documentation with issue reports and merged fixes to answer a specific behavior question.

### Investigate a dependency error

Search an error message with the library name, then compare issue reports and merged pull request passages for explanations and possible fixes.

### Check an API contract

Find README and documentation passages that describe a method's return value, default behavior, or required arguments before implementing a call.

### Prepare a dependency upgrade

Search for a named library, target version, and changed behavior. Use the returned passages and source links to assemble an upgrade checklist.

### Explain why behavior changed

Compare documentation with merged pull request passages to identify the reasoning behind an API or framework change.

### Draft a support answer with evidence

Turn relevant documentation and issue passages into an answer that links each explanation to its public source.

### Review recurring dependency problems

Repeat searches for a specific public project's error or compatibility problem and compare the returned passages with earlier findings.

## Overview

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

## Firecrawl developer search in other agents

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

## More ChatGPT guides

- [Firecrawl batch web scraping](https://spiral.ai/integrations/chatgpt/firecrawl-batch-web-scraping)
- [Firecrawl web page content](https://spiral.ai/integrations/chatgpt/firecrawl-web-page-content)
- [Exa web search](https://spiral.ai/integrations/chatgpt/exa-web-search)
- [Firecrawl web research](https://spiral.ai/integrations/chatgpt/firecrawl-web-research)
- [Exa web research](https://spiral.ai/integrations/chatgpt/exa-web-research)
- [Firecrawl web search](https://spiral.ai/integrations/chatgpt/firecrawl-web-search)

## Questions about Firecrawl developer search in ChatGPT

**Can ChatGPT use Firecrawl developer search?**

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

**How much does Firecrawl developer search cost in ChatGPT?**

$0.003492 per 10 results. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need a Firecrawl account to use Firecrawl developer search in ChatGPT?**

No. Spiral runs Firecrawl developer 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 developer search in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Firecrawl developer search runs?**

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

**What material does Firecrawl developer search cover?**

It covers public repository issues, merged pull requests, READMEs, and curated documentation sites. The documentation coverage is a selected index of sites.

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

A search can return up to 100 ranked results. The default is 10.

**Does it return source passages or just links?**

It returns matched passages in Markdown alongside source links. Tables and code blocks survive in the passage text.

**Does an empty search mean the documentation has no answer?**

A requested documentation source can be absent from the index. When its indexed flag is false, nothing from that source can match, regardless of the question.

**Can a successful search still be incomplete?**

Yes. A partial response means the deadline passed before every search stage finished, so it contains only the work completed by that point.

