goesByhc/cn-scraper-mcp

Overview

An MCP server that lets AI agents search Chinese internet platforms including Taobao, JD, Xiaohongshu, Zhihu, Weibo, Bilibili, ZSXQ, Douban, and Dianping. It exposes these sources through the Model Context Protocol so agents can query them programmatically.

Best for

Best for
Developers building AI agents that need access to Chinese web data across multiple platforms.

Use cases

• Search product listings and prices on Taobao and JD
• Pull posts and trends from Xiaohongshu and Weibo
• Retrieve Q&A content from Zhihu and reviews from Dianping

How to use

Install

pip install cn-scraper-mcp

Tools exposed

• CN_SCRAPER_TRANSPORT
• CN_SCRAPER_HOST
• CN_SCRAPER_PORT
• CN_SCRAPER_PATH
• taobao_search
• taobao_product
• jd_search
• jd_product
• pdd_search
• pdd_product_detail
• xiaohongshu_search
• xiaohongshu_note
• xiaohongshu_comments
• zhihu_search
• zhihu_hot_list
• zhihu_comments
• zhihu_answer
• zhihu_question_answers
• weibo_search
• weibo_hot_list

Tested with

Claude Code, Cursor

Notes

An MCP server that lets AI agents search Chinese internet platforms including Taobao, JD, Xiaohongshu, Zhihu, Weibo, Bilibili, ZSXQ, Douban, and Dianping. It exposes these sources through the Model Context Protocol so agents can query them programmatically.

34 stars on GitHub. Last updated 2026-07-29. Licensed MIT.

Use cases

• Search product listings and prices on Taobao and JD
• Pull posts and trends from Xiaohongshu and Weibo
• Retrieve Q&A content from Zhihu and reviews from Dianping

Pros

• Covers a wide range of major Chinese platforms in one tool
• Integrates with MCP, making it easy to plug into AI agent workflows
• Open source with a simple Python codebase

Cons

• Low star count suggests limited community adoption and testing
• Scraping endpoints may break as target sites change
• No explicit documentation or usage examples provided in the facts

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.