CrawlForge
首页Playground应用场景集成价格文档博客

Interactive Playground

Try CrawlForge tools live. Enter a URL, pick a tool, and see the results instantly.

5 free requests per session — no sign-up required

Input
1 credit

0/5 free requests used. Sign up for 1,000 free credits

Output

Enter a URL and select a tool to get started

Results will appear here

Popular Examples

Click an example to pre-fill the playground and try it out.

How It Works

Three simple steps to extract structured data from any web page.

Step 1

Enter a URL

Paste any web page URL or enter a search query.

Step 2

Pick a tool

Choose from 27 specialized extraction tools.

Step 3

Get results

Instantly receive structured data, ready for your AI pipeline.

All 27 Tools

A complete toolkit for web data extraction, organized by category.

Core Extraction

Site Analysis

Advanced

AI & Research

Utility

Use It In Your Code

Every playground request can be replicated with a single MCP call. Copy and integrate into your project.

Claude Desktop / Cursor

// Add to your MCP config
{
  "mcpServers": {
    "crawlforge": {
      "command": "npx",
      "args": [
        "@crawlforge/mcp-server"
      ]
    }
  }
}

// Then ask your AI assistant:
// "Extract the main content from
//  https://example.com using CrawlForge"

TypeScript / Node.js

import { CrawlForge } from '@crawlforge/sdk';

const cf = new CrawlForge({
  apiKey: process.env.CRAWLFORGE_API_KEY,
});

// Extract content from any URL
const result = await cf.extractContent({
  url: 'https://example.com',
  format: 'markdown',
});

console.log(result.content);
// Credits used: 2

Frequently Asked Questions

Common questions about the CrawlForge playground.

Do I need an account to use the playground?

No. You get 5 free requests per session without signing up. Create a free account to unlock 1,000 credits and remove the session limit.

Are playground results the same as the API?

Yes. The playground uses the same CrawlForge MCP tools and returns identical results. Copy any result directly into your application.

How are credits calculated?

Each tool has a fixed credit cost from 1 to 10 credits per request. Simple extractions cost 1-2 credits, while advanced tools like deep_research cost 10 credits.

Can I scrape any website?

CrawlForge respects robots.txt and rate limits. Some sites may block automated access. Use stealth_mode (3 credits) for sites that require browser-like behavior.

What makes CrawlForge different from other scraping tools?

CrawlForge is MCP-native — built from the ground up on the Model Context Protocol. This means your AI agents can use CrawlForge tools directly without REST wrappers or custom integrations.

How do I integrate CrawlForge into my project?

Add CrawlForge to your MCP config (Claude Desktop, Cursor, Windsurf) or use the API directly with your API key. Check our docs for step-by-step setup guides.

18

Specialized Tools

1,000

Free Credits

1-10

Credits Per Request

MCP

Native Protocol

Ready for production?

Sign up for 1,000 free credits and integrate CrawlForge into your AI pipeline.

Get Started FreeView Documentation

页脚

CrawlForge

面向 AI Agent 的企业级网页抓取。27 个专业 MCP 工具,专为构建智能系统的现代开发者而设计。

产品

  • 功能
  • Playground
  • 价格
  • 应用场景
  • 集成
  • 替代方案
  • 更新日志

资源

  • 快速上手
  • API 参考
  • 模板
  • 指南
  • 博客
  • 术语表
  • 常见问题
  • 网站地图

开发者

  • MCP 协议
  • Claude Desktop
  • Cursor IDE
  • LangChain
  • LlamaIndex

公司

  • 关于我们
  • 联系我们
  • 隐私政策
  • 服务条款
  • 可接受使用政策
  • Cookie

保持更新

获取新工具和新功能的最新动态。

基于 Next.js 和 MCP 协议构建

© 2025-2026 CrawlForge。保留所有权利。