Crawl MCP
未认领Crawl4AI MCP Server: Extract content from web pages, PDFs, Office docs, YouTube videos with AI-powered summarization. 17 tools, token reduction, production-ready.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'walksoda-crawl-mcp' -- 'uvx' '--from' 'git+https://github.com/walksoda/crawl-mcp' 'crawl-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
19 个工具中显示 19 个
文档中列出的工具 (19)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
batch_crawl
Crawl multiple URLs with fallback (max 3 URLs)
batch_extract_youtube_transcripts
Extract transcripts from multiple YouTube videos (max 3)
batch_search_google
Perform multiple Google searches (max 3)
crawl_url
Extract web page content with JavaScript support
crawl_url_with_fallback
Crawl with fallback strategies for anti-bot sites
deep_crawl_site
Crawl multiple pages from a site with configurable depth
enhanced_process_large_content
Process large content with chunking and BM25 filtering
extract_entities
Extract entities (emails, phones, etc.) from web pages
extract_structured_data
Extract structured data using CSS selectors or LLM
extract_youtube_comments
Extract YouTube video comments with pagination
extract_youtube_transcript
Extract YouTube transcripts with timestamps
get_search_genres
Get available search genres
get_supported_file_formats
Get supported file formats and capabilities
get_youtube_video_info
Get YouTube video metadata and transcript availability
intelligent_extract
Extract specific data from web pages using LLM
multi_url_crawl
Multi-URL crawl with pattern-based config (max 5 URL patterns)
process_file
Convert PDF, Word, Excel, PowerPoint, ZIP to markdown
search_and_crawl
Search Google and crawl top results
search_google
Search Google with genre filtering