---
title: Xcrawl: AI向けWebデータAPIとMCPサーバー
tags: 
author: [PENG JIAFU](https://docswell.com/user/3085317562)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/4JM6VYLQEW.jpg?width=480
description: Xcrawl（https://www.xcrawl.ai/）はURLや検索クエリから、整ったMarkdown・JSON・HTML・スクリーンショットを返すWebデータAPIです。Scrape・Map・Crawl・Searchの4種類のエンドポイント、Python/Node.js SDK、CLI（@xcrawl/cli）、MCPサーバー（npm: xcrawl-mcp）を提供し、LLMアプリやRAGにリアルタイムのWebデータを取り込めます。
published: November 15, 26
canonical: https://docswell.com/s/3085317562/54NPNG-2026-11-15-052247
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/4JM6VYLQEW.jpg)

XCrawl: web data API for AI builders
Website: https://www.xcrawl.ai/ Docs: https://docs.xcrawl.ai/
What it does
• Scrape a single URL into Markdown, JSON, HTML or a screenshot.
• Crawl a whole site with depth and scope rules, asynchronously, and poll
for progress.
• Map every URL on a domain.
• Search the web and feed results into the next step.
JavaScript rendering, proxy rotation and retries are handled on XCrawl's side, so
your code receives clean, LLM-ready output.
Ways to use it
Python SDK: pip install xcrawl
Node.js SDK: @xcrawl/xcrawl on npm
CLI: @xcrawl/cli
MCP server: npx xcrawl-mcp for Claude Code, Cursor and other MCP
clients
• n8n node: n8n-nodes-xcrawl
•
•
•
•
Typical RAG workflow
Map a documentation site, scrape the pages you need as Markdown, split them
by headings, embed the chunks and store them in your vector database. Re-run
on a schedule to keep the index fresh.
New accounts start with 1,000 free credits. Learn more at www.xcrawl.ai.