CN Scraper MCP

让 AI Agent 直接搜索中国互联网 - - 淘宝、京东、小红书、知乎、微博、B站、知识星球……不再被反爬墙挡住。每个 AI Agent（Codex、Claude Code、Cursor、Trae）都能搜网页，但中文平台通常需要登录态、浏览器环境或平台专用参数：. It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-07-29 · ★ 28 · #19 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install CN Scraper MCP

before you install - you'll need

Set CN_SCRAPER_TRANSPORT, CN_SCRAPER_HOST, CN_SCRAPER_PORT, CN_SCRAPER_PATH before connecting.

Claude Code

claude mcp add goesbyhc-cn-scraper-mcp -- uvx cn-scraper-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "goesbyhc-cn-scraper-mcp": {
      "command": "uvx",
      "args": [
        "cn-scraper-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-07-13 - young repo, little track record yet

license MIT - declared in the repository

pypi package cn-scraper-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.goesByhc is GitHub-verified and matches the repo owner

03 · What CN Scraper MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.5.0 · 2026-07-29

Added · Release workflow now publishes Docker images to GitHub Container Registry (ghcr.io/goesbyhc/cn-scraper-mcp) alongside PyPI distributions. · Shared ACTION_REQUIRED MCP error shape for manual login, captcha, and…

v0.4.1 · 2026-07-21

Changed · Added MCP registry metadata (mcp-name in README.md and server.json) and aligned release metadata for external MCP directories.

v0.4.0 · 2026-07-17

新增 · 新增豆瓣条目搜索、条目详情和短评/影评 MCP 工具。 · 新增大众点评商户搜索、商户详情和评价 MCP 工具。 · 豆瓣和大众点评接入本地 Cookie 管理、guided_login 和 harvest_cookies。 · 登录凭证继续只保存在用户本机，不通过 MCP 返回 Cookie 值。 · 增加两个平台的输入校验、单元测试和 MCP 契约测试。 · 改进 · 豆瓣请求使用浏览器 TLS 指纹，并在 JSON…

04 · Who maintains CN Scraper MCP

CN Scraper MCP is maintained by goesbyhc. It's the only MCP server we track from this author; the repo dates to Jul 2026.

05 · Facts

repository: github.com/goesbyhc/cn-scraper-mcp
category: web scraping - ranked #19 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 6 releases in the last 90 days (latest 2026-07-29)
registry: io.github.goesByhc/cn-scraper-mcp (active, first published 2026-07-21)
packages: pypi:cn-scraper-mcp

06 · CN Scraper MCP FAQ

What is CN Scraper MCP?

Is CN Scraper MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-29 and it shipped 6 releases in the last 90 days. We re-verify nightly.

How do I install CN Scraper MCP?

Run `uvx cn-scraper-mcp`. The README documents 4 environment variables (CN_SCRAPER_TRANSPORT, CN_SCRAPER_HOST, CN_SCRAPER_PORT…) to set first. Set CN_SCRAPER_TRANSPORT, CN_SCRAPER_HOST, CN_SCRAPER_PORT, CN_SCRAPER_PATH before connecting. You can also paste the ready-made client config above.

Does CN Scraper MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to CN Scraper MCP

Alternatives to CN Scraper MCP

Maintained web scraping servers if CN Scraper MCP isn't the fit.

Pairs well with

Servers that cover what CN Scraper MCP doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · HasData Google Maps · Has Data · HasData Instagram · Ragstack · Web Search

More Python MCP servers · Endnote MCP · Goodeye · Link · Ipybox · Chart Library - Pattern Intelligence · see all