🛠️ 開発・MCP コミュニティ 🔴 エンジニア向け 👤 エンジニア・AI開発者

🛠️ Firecrawl

firecrawl

ウェブサイトから情報を抽出したり、サイト全体を巡回してURLを整理したり、ウェブ検索を実行したりするなど、ウェブコンテンツを効率的に収集・分析する際に活用できるSkill。

⚡ ⏱ ライブラリ調査+組込半日 → 1時間

📺 まず動画で見る(YouTube)

▶ 【衝撃】最強のAIエージェント「Claude Code」の最新機能・使い方・プログラミングをAIで効率化する超実践術を解説! ↗

※ jpskill.com 編集部が参考用に選んだ動画です。動画の内容と Skill の挙動は厳密には一致しないことがあります。

📜 元の英語説明(参考)

Firecrawl API integration with managed authentication. Scrape, crawl, map, and search web content. Use this skill when users want to extract content from websites, crawl entire sites, map URLs, or search the web. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

🇯🇵 日本人クリエイター向け解説

一言でいうと

※ jpskill.com 編集部が日本のビジネス現場向けに補足した解説です。Skill本体の挙動とは独立した参考情報です。

⚡ おすすめ: コマンド1行でインストール(60秒)

下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。ダウンロード → 解凍 → 配置まで全自動。

🍎 Mac / 🐧 Linux

mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o firecrawl.zip https://jpskill.com/download/4819.zip && unzip -o firecrawl.zip && rm firecrawl.zip

🪟 Windows (PowerShell)

$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/4819.zip -OutFile "$d\firecrawl.zip"; Expand-Archive "$d\firecrawl.zip" -DestinationPath $d -Force; ri "$d\firecrawl.zip"

完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。

💾 手動でダウンロードしたい(コマンドが難しい人向け)

1. 下の青いボタンを押して firecrawl.zip をダウンロード
2. ZIPファイルをダブルクリックで解凍 → firecrawl フォルダができる
3. そのフォルダを C:\Users\あなたの名前\.claude\skills\(Win)または ~/.claude/skills/(Mac)へ移動
4. Claude Code を再起動

⬇ .zip でダウンロード(推奨) ⬇ .skill 形式(上級者用) 元のソース ↗

⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。

🎯 このSkillでできること

下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。

📦 インストール方法 (3ステップ)

1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
3. 展開してできたフォルダを、ホームフォルダの .claude/skills/ に置く
- · macOS / Linux: ~/.claude/skills/
- · Windows: %USERPROFILE%\.claude\skills\

Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。

詳しい使い方ガイドを見る →

最終更新: 2026-05-17
取得日時: 2026-05-18
同梱ファイル: 2

💬 こう話しかけるだけ — サンプルプロンプト

› Firecrawl を使って、最小構成のサンプルコードを示して
› Firecrawl の主な使い方と注意点を教えて
› Firecrawl を既存プロジェクトに組み込む方法を教えて

これをClaude Code に貼るだけで、このSkillが自動発動します。

📖 Skill本文(日本語訳)

※ 原文(英語/中国語)を Gemini で日本語化したものです。Claude 自身は原文を読みます。誤訳がある場合は原文をご確認ください。

Firecrawl

マネージド認証でFirecrawl APIにアクセスできます。ウェブページのスクレイピング、ウェブサイト全体のクロール、サイトURLのマッピング、および完全なコンテンツ抽出によるウェブ検索が可能です。

クイックスタート

# Scrape a webpage
python <<'EOF'
import urllib.request, os, json
data = json.dumps({"url": "https://example.com", "formats": ["markdown"]}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

ベースURL

https://gateway.maton.ai/firecrawl/{native-api-path}

{native-api-path}を実際のFirecrawl APIエンドポイントパスに置き換えてください。このゲートウェイはapi.firecrawl.devへのリクエストをプロキシし、APIキーを自動的に挿入します。

認証

すべてのリクエストには、AuthorizationヘッダーにMaton APIキーが必要です。

Authorization: Bearer $MATON_API_KEY

環境変数: APIキーをMATON_API_KEYとして設定してください。

export MATON_API_KEY="YOUR_API_KEY"

APIキーの取得

maton.aiでサインインまたはアカウントを作成します。
maton.ai/settingsにアクセスします。
APIキーをコピーします。

接続管理

Firecrawl接続はhttps://ctrl.maton.aiで管理できます。

接続のリスト表示

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=firecrawl&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

接続の作成

python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'firecrawl'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

接続の取得

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

レスポンス:

{
  "connection": {
    "connection_id": "b5449045-2dcd-4e99-816f-65f80511affb",
    "status": "ACTIVE",
    "creation_time": "2026-03-11T09:49:09.917114Z",
    "last_updated_time": "2026-03-11T09:49:27.616143Z",
    "url": "https://connect.maton.ai/?session_token=...",
    "app": "firecrawl",
    "metadata": {},
    "method": "API_KEY"
  }
}

接続の削除

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

接続の指定

複数のFirecrawl接続がある場合は、Maton-Connectionヘッダーでどの接続を使用するかを指定してください。

python <<'EOF'
import urllib.request, os, json
data = json.dumps({"url": "https://example.com"}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
req.add_header('Maton-Connection', 'b5449045-2dcd-4e99-816f-65f80511affb')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

省略した場合、ゲートウェイはデフォルト（最も古い）のアクティブな接続を使用します。

APIリファレンス

Scrape

POST /firecrawl/v2/scrape

単一のウェブページからコンテンツを抽出します。

必須パラメーター:

url (string): スクレイピングするウェブページのURL

オプションパラメーター:

formats (array): 出力形式 - "markdown", "html", "json", "screenshot", "links" (デフォルト: ["markdown"])
onlyMainContent (boolean): メインコンテンツのみを抽出し、ヘッダー/フッターを除外します (デフォルト: true)
includeTags (array): 含めるHTMLタグ
excludeTags (array): 除外するHTMLタグ
waitFor (integer): スクレイピング前に待機するミリ秒数 (デフォルト: 0)
timeout (integer): リクエストのタイムアウト時間（ミリ秒） (デフォルト: 30000, 最大: 300000)
mobile (boolean): モバイルデバイスをエミュレートします (デフォルト: false)
actions (array): スクレイピング前に実行するブラウザアクション
headers (object): カスタムHTTPヘッダー
blockAds (boolean): 広告とクッキーバナーをブロックします (デフォルト: true)

例:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "url": "https://docs.firecrawl.dev",
    "formats": ["markdown", "html"],
    "onlyMainContent": True,
    "waitFor": 1000
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

レスポンス:

{
  "success": true,
  "data": {
    "markdown": "# Example Domain\n\nThis domain is for use in documentation...",
    "metadata": {
      "title": "Example Domain",
      "language": "en",
      "sourceURL": "https://example.com",
      "url": "https://example.com/",
      "statusCode": 200,
      "contentType": "text/html",
      "creditsUsed": 1
    }
  }
}

Crawl (開始)

POST /firecrawl/v2/crawl

ウェブサイト全体のクロールを開始します。ステータスをポーリングするためのクロールIDを返します。

必須パラメーター:

url (string): クロールを開始するベースURL

オプションパラメーター:

limit (integer): クロールする最大ページ数 (デフォルト: 10000)
maxDepth (integer): 最大クロール深度
`includ

(原文がここで切り詰められています)

📜 原文 SKILL.md(Claudeが読む英語/中国語)を展開

Firecrawl

Access the Firecrawl API with managed authentication. Scrape webpages, crawl entire websites, map site URLs, and search the web with full content extraction.

Quick Start

# Scrape a webpage
python <<'EOF'
import urllib.request, os, json
data = json.dumps({"url": "https://example.com", "formats": ["markdown"]}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Base URL

https://gateway.maton.ai/firecrawl/{native-api-path}

Replace {native-api-path} with the actual Firecrawl API endpoint path. The gateway proxies requests to api.firecrawl.dev and automatically injects your API key.

Authentication

All requests require the Maton API key in the Authorization header:

Authorization: Bearer $MATON_API_KEY

Environment Variable: Set your API key as MATON_API_KEY:

export MATON_API_KEY="YOUR_API_KEY"

Getting Your API Key

Sign in or create an account at maton.ai
Go to maton.ai/settings
Copy your API key

Connection Management

Manage your Firecrawl connections at https://ctrl.maton.ai.

List Connections

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=firecrawl&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Create Connection

python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'firecrawl'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Get Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "connection": {
    "connection_id": "b5449045-2dcd-4e99-816f-65f80511affb",
    "status": "ACTIVE",
    "creation_time": "2026-03-11T09:49:09.917114Z",
    "last_updated_time": "2026-03-11T09:49:27.616143Z",
    "url": "https://connect.maton.ai/?session_token=...",
    "app": "firecrawl",
    "metadata": {},
    "method": "API_KEY"
  }
}

Delete Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Specifying Connection

If you have multiple Firecrawl connections, specify which one to use with the Maton-Connection header:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({"url": "https://example.com"}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
req.add_header('Maton-Connection', 'b5449045-2dcd-4e99-816f-65f80511affb')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

If omitted, the gateway uses the default (oldest) active connection.

API Reference

Scrape

POST /firecrawl/v2/scrape

Extract content from a single webpage.

Required Parameters:

url (string): The webpage URL to scrape

Optional Parameters:

formats (array): Output formats - "markdown", "html", "json", "screenshot", "links" (default: ["markdown"])
onlyMainContent (boolean): Extract only main content, exclude headers/footers (default: true)
includeTags (array): HTML tags to include
excludeTags (array): HTML tags to exclude
waitFor (integer): Milliseconds to wait before scraping (default: 0)
timeout (integer): Request timeout in ms (default: 30000, max: 300000)
mobile (boolean): Emulate mobile device (default: false)
actions (array): Browser actions to perform before scraping
headers (object): Custom HTTP headers
blockAds (boolean): Block ads and cookie banners (default: true)

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "url": "https://docs.firecrawl.dev",
    "formats": ["markdown", "html"],
    "onlyMainContent": True,
    "waitFor": 1000
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "data": {
    "markdown": "# Example Domain\n\nThis domain is for use in documentation...",
    "metadata": {
      "title": "Example Domain",
      "language": "en",
      "sourceURL": "https://example.com",
      "url": "https://example.com/",
      "statusCode": 200,
      "contentType": "text/html",
      "creditsUsed": 1
    }
  }
}

Crawl (Start)

POST /firecrawl/v2/crawl

Start crawling an entire website. Returns a crawl ID for status polling.

Required Parameters:

url (string): The base URL to start crawling from

Optional Parameters:

limit (integer): Maximum pages to crawl (default: 10000)
maxDepth (integer): Maximum crawl depth
includePaths (array): Regex patterns for URLs to include
excludePaths (array): Regex patterns for URLs to exclude
allowSubdomains (boolean): Enable subdomain crawling
allowExternalLinks (boolean): Follow external links
scrapeOptions (object): Options for each page scrape (formats, onlyMainContent, etc.)
webhook (string): Webhook URL for completion notification

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "url": "https://example.com",
    "limit": 10,
    "scrapeOptions": {
        "formats": ["markdown"]
    }
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/crawl', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "id": "019cdc53-0acf-76ec-a80c-3ead753b2730",
  "url": "https://api.firecrawl.dev/v1/crawl/019cdc53-0acf-76ec-a80c-3ead753b2730"
}

Crawl (Get Status)

GET /firecrawl/v2/crawl/{id}

Get the status and results of a crawl job.

Path Parameters:

id (string): The crawl job ID

Example:

python <<'EOF'
import urllib.request, os, json
crawl_id = "019cdc53-0acf-76ec-a80c-3ead753b2730"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/crawl/{crawl_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "status": "completed",
  "completed": 2,
  "total": 2,
  "creditsUsed": 2,
  "expiresAt": "2026-03-12T09:56:00.000Z",
  "data": [
    {
      "markdown": "# Example Domain\n\nThis domain is for use in documentation...",
      "metadata": {
        "title": "Example Domain",
        "sourceURL": "https://example.com",
        "statusCode": 200
      }
    }
  ]
}

Status Values:

scraping - Crawl in progress
completed - Crawl finished successfully
failed - Crawl failed

Crawl (Cancel)

DELETE /firecrawl/v2/crawl/{id}

Cancel an in-progress crawl job.

Path Parameters:

id (string): The crawl job ID

Example:

python <<'EOF'
import urllib.request, os, json
crawl_id = "019cdc53-0acf-76ec-a80c-3ead753b2730"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/crawl/{crawl_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "status": "cancelled"
}

Map

POST /firecrawl/v2/map

Get all URLs from a website without scraping content.

Required Parameters:

url (string): The starting URL

Optional Parameters:

search (string): Query to order results by relevance
limit (integer): Maximum links to return (default: 5000, max: 100000)
includeSubdomains (boolean): Include subdomains (default: true)
sitemap (string): Sitemap handling - "skip", "include", "only" (default: "include")
ignoreQueryParameters (boolean): Exclude URLs with query params (default: true)
timeout (integer): Timeout in milliseconds

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "url": "https://docs.firecrawl.dev",
    "limit": 100,
    "includeSubdomains": False
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/map', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "links": [
    "https://docs.firecrawl.dev",
    "https://docs.firecrawl.dev/api-reference",
    "https://docs.firecrawl.dev/introduction"
  ]
}

Search

POST /firecrawl/v2/search

Search the web and get full page content for each result.

Required Parameters:

query (string): Search query (max 500 characters)

Optional Parameters:

limit (integer): Number of results (default: 5, max: 100)
sources (array): Search types - "web", "images", "news" (default: ["web"])
country (string): ISO country code (default: "US")
location (string): Geographic targeting (e.g., "Germany")
tbs (string): Time filter - "qdr:d" (day), "qdr:w" (week), "qdr:m" (month), "qdr:y" (year)
timeout (integer): Timeout in ms (default: 60000)
scrapeOptions (object): Options for content extraction

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "query": "web scraping best practices",
    "limit": 5,
    "scrapeOptions": {
        "formats": ["markdown"]
    }
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/search', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "data": [
    {
      "url": "https://example.com/article",
      "title": "Web Scraping Best Practices",
      "description": "Learn the best practices for web scraping...",
      "markdown": "# Web Scraping Best Practices\n\n..."
    }
  ],
  "creditsUsed": 5
}

Batch Scrape (Start)

POST /firecrawl/v2/batch/scrape

Scrape multiple URLs in a single batch job.

Required Parameters:

urls (array): List of URLs to scrape

Optional Parameters:

formats (array): Output formats (default: ["markdown"])
onlyMainContent (boolean): Extract only main content (default: true)
webhook (string): Webhook URL for completion notification

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "urls": ["https://example.com", "https://example.org"],
    "formats": ["markdown"]
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/batch/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "id": "019cdc59-56b9-7096-a9f9-95fcc92a3a75",
  "url": "https://api.firecrawl.dev/v1/batch/scrape/019cdc59-56b9-7096-a9f9-95fcc92a3a75"
}

Batch Scrape (Get Status)

GET /firecrawl/v2/batch/scrape/{id}

Get the status and results of a batch scrape job.

Path Parameters:

id (string): The batch scrape job ID

Example:

python <<'EOF'
import urllib.request, os, json
batch_id = "019cdc59-56b9-7096-a9f9-95fcc92a3a75"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/batch/scrape/{batch_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "status": "completed",
  "completed": 2,
  "total": 2,
  "creditsUsed": 2,
  "expiresAt": "2026-03-12T10:02:54.000Z",
  "data": [
    {
      "markdown": "# Example Domain\n\n...",
      "metadata": {
        "title": "Example Domain",
        "sourceURL": "https://example.com",
        "statusCode": 200
      }
    }
  ]
}

Batch Scrape (Cancel)

DELETE /firecrawl/v2/batch/scrape/{id}

Cancel an in-progress batch scrape job.

Path Parameters:

id (string): The batch scrape job ID

Batch Scrape (Get Errors)

GET /firecrawl/v2/batch/scrape/{id}/errors

Get errors from a batch scrape job.

Path Parameters:

id (string): The batch scrape job ID

Response:

{
  "errors": [],
  "robotsBlocked": []
}

Crawl (Get Errors)

GET /firecrawl/v2/crawl/{id}/errors

Get errors from a crawl job.

Path Parameters:

id (string): The crawl job ID

Example:

python <<'EOF'
import urllib.request, os, json
crawl_id = "019cdc53-0acf-76ec-a80c-3ead753b2730"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/crawl/{crawl_id}/errors')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "errors": [],
  "robotsBlocked": []
}

Crawl (Get Active)

GET /firecrawl/v2/crawl/active

Get all active crawl jobs.

Example:

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/crawl/active')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "crawls": []
}

Extract (Start)

POST /firecrawl/v2/extract

Extract structured data from URLs using AI.

Required Parameters:

urls (array): List of URLs to extract from
prompt (string): Natural language description of what to extract

Optional Parameters:

schema (object): JSON schema for structured output
scrapeOptions (object): Options for scraping

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "urls": ["https://example.com"],
    "prompt": "Extract the main heading and description"
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/extract', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "id": "019cdc59-977b-774b-b584-af2af45c055b",
  "urlTrace": []
}

Extract (Get Status)

GET /firecrawl/v2/extract/{id}

Get the status and results of an extract job.

Path Parameters:

id (string): The extract job ID

Example:

python <<'EOF'
import urllib.request, os, json
extract_id = "019cdc59-977b-774b-b584-af2af45c055b"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/extract/{extract_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "data": [
    {
      "heading": "Example Domain",
      "description": "This domain is for use in documentation..."
    }
  ],
  "status": "completed",
  "expiresAt": "2026-03-11T16:03:05.000Z"
}

Browser (Create Session)

POST /firecrawl/v2/browser

Create an interactive browser session for manual control via CDP.

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/browser', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "id": "019cdc5d-5c9d-732e-a7bd-f095a96a2bb1",
  "cdpUrl": "wss://browser.firecrawl.dev/cdp/...",
  "liveViewUrl": "https://liveview.firecrawl.dev/...",
  "interactiveLiveViewUrl": "https://liveview.firecrawl.dev/...",
  "expiresAt": "2026-03-11T10:17:12.409Z"
}

Browser (List Sessions)

GET /firecrawl/v2/browser

List all active browser sessions.

Example:

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/browser')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "sessions": [
    {
      "id": "019cdc5d-5c9d-732e-a7bd-f095a96a2bb1",
      "status": "active",
      "cdpUrl": "wss://browser.firecrawl.dev/cdp/...",
      "liveViewUrl": "https://liveview.firecrawl.dev/..."
    }
  ]
}

Browser (Delete Session)

DELETE /firecrawl/v2/browser/{id}

Delete a browser session.

Path Parameters:

id (string): The browser session ID

Agent (Start)

POST /firecrawl/v2/agent

Start an AI agent to autonomously navigate and extract data.

Required Parameters:

prompt (string): Description of what data to extract (max 10,000 chars)

Optional Parameters:

urls (array): URLs to constrain the agent to
schema (object): JSON schema for structured output
maxCredits (integer): Spending limit (default: 2500)
strictConstrainToURLs (boolean): Only visit provided URLs
model (string): "spark-1-mini" (default, cheaper) or "spark-1-pro" (higher accuracy)

Example:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "prompt": "Find the pricing information",
    "urls": ["https://example.com"],
    "model": "spark-1-mini"
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/agent', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "id": "019cdc5d-a2d4-728c-9c91-e9eae475568f"
}

Agent (Get Status)

GET /firecrawl/v2/agent/{id}

Get the status and results of an agent job.

Path Parameters:

id (string): The agent job ID

Example:

python <<'EOF'
import urllib.request, os, json
agent_id = "019cdc5d-a2d4-728c-9c91-e9eae475568f"
req = urllib.request.Request(f'https://gateway.maton.ai/firecrawl/v2/agent/{agent_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "success": true,
  "status": "completed",
  "model": "spark-1-pro",
  "data": {...},
  "expiresAt": "2026-03-12T10:07:30.055Z"
}

Agent (Cancel)

DELETE /firecrawl/v2/agent/{id}

Cancel an in-progress agent job.

Path Parameters:

id (string): The agent job ID

Browser Actions

Use actions parameter to interact with pages before scraping:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({
    "url": "https://example.com",
    "formats": ["markdown", "screenshot"],
    "actions": [
        {"type": "wait", "milliseconds": 2000},
        {"type": "click", "selector": "#load-more"},
        {"type": "scroll", "direction": "down", "amount": 500},
        {"type": "screenshot"}
    ]
}).encode()
req = urllib.request.Request('https://gateway.maton.ai/firecrawl/v2/scrape', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Available Actions:

wait - Wait for specified milliseconds
click - Click an element by CSS selector
write - Type text into an input field
scroll - Scroll the page
screenshot - Take a screenshot
execute - Run custom JavaScript

Code Examples

JavaScript

const response = await fetch('https://gateway.maton.ai/firecrawl/v2/scrape', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${process.env.MATON_API_KEY}`
  },
  body: JSON.stringify({
    url: 'https://example.com',
    formats: ['markdown']
  })
});
const data = await response.json();
console.log(data.data.markdown);

Python

import os
import requests

response = requests.post(
    'https://gateway.maton.ai/firecrawl/v2/scrape',
    headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'},
    json={
        'url': 'https://example.com',
        'formats': ['markdown']
    }
)
data = response.json()
print(data['data']['markdown'])

Notes

Scrape uses 1 credit per page (basic proxy)
Enhanced proxy for anti-bot sites uses up to 5 credits
Crawl results expire after 24 hours
Maximum timeout is 300,000ms (5 minutes)
Use onlyMainContent: true to get cleaner output without navigation/footer
IMPORTANT: When piping curl output to jq or other commands, environment variables like $MATON_API_KEY may not expand correctly in some shell environments

Error Handling

Status	Meaning
400	Missing Firecrawl connection or invalid parameters
401	Invalid or missing Maton API key
402	Payment required (Firecrawl credits exhausted)
409	Conflict (e.g., crawl already completed)
429	Rate limited
4xx/5xx	Passthrough error from Firecrawl API

Troubleshooting: API Key Issues

Check that the MATON_API_KEY environment variable is set:

echo $MATON_API_KEY

Verify the API key is valid by listing connections:

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Troubleshooting: Invalid App Name

Ensure your URL path starts with firecrawl. For example:

Correct: https://gateway.maton.ai/firecrawl/v2/scrape
Incorrect: https://gateway.maton.ai/v2/scrape

Resources

同梱ファイル

※ ZIPに含まれるファイル一覧。`SKILL.md` 本体に加え、参考資料・サンプル・スクリプトが入っている場合があります。

📄 SKILL.md (24,619 bytes)
📎 LICENSE.txt (1,072 bytes)