MCP.Market

Caishi MCP server

by ZhongQuinnKing·io.github.ZhongQuinnKing/caishi·v1.0.1·1 stars

Read Bilibili, Douyin, Xiaohongshu and any web page via your own logged-in Chrome.

A89/100grade A
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed Caishi yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Caishi tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-12 · same rubric, same numbers if you re-run it

no findings
  • Code scan7 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Caishi compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 80% of 48,255 servers
GitHub stars
1
more than 65% of 28,688 servers

Install Caishi in Claude Code, Cursor or VS Code

Runs npx -y caishi-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add caishi -- npx -y caishi-mcp
Add to Cursor

What the publisher says

From the Caishi repository's README, as published. We do not edit it. Read it on GitHub

采诗 · 给 AI 用的中文互联网能力包

原作者:ZhongQuinnKing(主号署名)

许可:见 LICENSE(分层:代码 MIT,内容与文档 CC BY-NC-ND 4.0;五档:免费用/自改自由/转发署名/改版发布先授权/商用零豁免)

商用与合作:请先联系(通道:本仓库 issue)

English TL;DR — A capability pack that lets AI agents read the Chinese internet:

Douyin, Bilibili, Xiaohongshu, WeChat Official Accounts, Zhihu, Toutiao + 30+ academic /

developer / lifestyle sites. Read-only, reuses your own browser sessions, one link at a time —

no scraping at scale.

把你 AI 的眼睛接到中文互联网上——抖音、小红书、B站、微博、知乎、公众号、头条, 一条命令读内容。给 Claude Code 这类能跑命令行的 Agent 直接用。

仓库地址:https://github.com/ZhongQuinnKing/caishi (平台变化、命令失效,欢迎提 issue)

它不爬虫、不做批量:所有请求都走你自己的浏览器会话(opencli 浏览器桥), 复用你已经登录的账号,就像你自己在浏览器里看一样。

能干什么

本包自研补充共九件 14 条命令(抖音 detail / comments / collection、小红书 find / read、 IMSLP 与弹琴吧乐谱、dblp 学术检索、网页正文读取),随包附带装在 clis/ 目录,安装即就位; 其余来自 opencli 官方适配器。逐平台实测状态与已知坑见 平台状态表.md。

一线 AI(MCP)

不只有命令行的 AI 能用——通过官方 opencli-mcp (Apache-2.0),Claude Desktop、Cursor、Codex、DeepSeek Harness 等任何 MCP 客户端都能接入 同一套能力(同一个浏览器、同一份登录态)。四站命令已上架(B站视频/抖音详情/小红书笔记/ 任意网页正文),随独立包 caishi-mcp 发布:npm install -g caishi-mcp。 装法与边界见 caishi-mcp/README.md 与 MCP.md。

另带三个小工具

输出统一格式 Markdown;--save 目录 存成文件。跨平台就是它。

  • zhread "<链接>" —— 一条命令读中文互联网:自动识别平台(抖音/B站/公众号/知乎/小红书/乐谱站),

(会依次打开各平台页面并事先提示)。平台哪天坏了,先跑它。

  • zhcheck —— 平台体检:默认轻检(只查浏览器桥,不开任何页面);--deep 才逐平台探测

修不了的问题给出上报模板(平台改版是常态,修好的版本当天就能到)。一个查、一个修。

  • zhupdate —— 自更新与修复:比对远程最新版本,git 安装自动拉取并重跑部署;

安装

前提:macOS(或任意能装 Node 的桌面系统)+ Chrome/Chromium。

→ 选 ~/.opencli/extension(脚本会把扩展文件准备好,商店装了也行)

  1. 运行 bash install.sh(自动装 opencli、下载浏览器扩展文件、装入自研命令)
  2. 手动一步:Chrome 打开 chrome://extensions → 开发者模式 → 「加载已解压的扩展程序」
  1. 按需登录平台:在同一个浏览器里打开对应网站扫码登录即可(一次长期有效)

用法(给 AI 的一句话)

"帮我看看这条抖音说了啥 https://v.douyin.com/xxxx/"

"在小红书上搜一下钢琴教学,把前几条列出来"

"把这个公众号文章导出成 markdown"

Agent 会自己走上表里对应的命令。

在国产 AI(豆包等)上使用

本包自带的 skills/zh-web 技能是跨环境的,国产 AI 也能装:

只有对话的(豆包等)走"无命令路径"——借用 AI 自身的联网能力读公开页面,读不动的 如实告诉你、请你贴文字或截图

  1. 下载本仓库,把 skills/zh-web 文件夹(含 SKILL.md)拖进豆包「我的技能」——或对豆包说:"请安装这个 skill:https://github.com/ZhongQuinnKing/caishi"
  2. 装上后它会自己看环境:能跑命令的(Claude Code / Codex 等)走完整命令路由;

一句话说明白:深度读取(评论、收藏、字幕、导出……)需要命令行环境;纯对话环境能拿到哪些,技能里逐平台写清楚了。

已知坑与纪律(重要,用前必读)

要一个开一个、要几个开几个;未指令的绝不打开。登录同样按需。

  • 一切以你的指令为准:安装本身不打开任何网页;平台页面只在你明确提出使用它时才出现——
  • 只读,不批量,不互动。频率克制——账号安全第一,工具不替你们担责。
  • 登录建议用测试号/小号,别把主力账号往上挂。
  • 小红书会话短命:关掉浏览器就掉登录,用的时候保持浏览器开着;撞上"设备超限"风控就停一两天再登。
  • 抖音/小红书等平台改版频繁,接口可能失效——坏了欢迎提 issue。
  • 本包不含需要翻墙的平台(YouTube、Twitter 等),它们不在此列。

姊妹篇

同一个家族的另外三个免费开源项目:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Caishi: common questions

Is Caishi MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Caishi safety report
How do I install Caishi?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Caishi need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Caishi maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v1.0.1.
What can I use instead of Caishi?
Servers from other publishers that do the same job: Front-End Checklist MCP server.
How does Caishi compare with other MCP servers?
safety score 89/100 (higher than 80% of 48,255 servers); github stars 1 (more than 65% of 28,688 servers). Full comparison.

Alternatives to Caishi

Same job from other publishers: the closest match first, then the best rated.

  • Front-End Checklist
    Review frontend code and live pages against 386 quality-gated web development rules.
    A