SoloMCN — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ymybxx · Agent Tool · ★ 53

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is SoloMCN safe to install? View the security audit →

About SoloMCN

SoloMCN https://github.com/user-attachments/assets/5b00fe30-f189-4c17-aa7a-f6080da1048b 把 Claude Code 变成你的短视频团队 不搭工作流,直接让 Claude 干活。从国内热榜、推特热帖,到抖音、小红书、B站、YouTube、推特发布,一个人运营一个账号矩阵,每一步都是 Claude 亲手做的。 English · MIT License · Powered by Claude Code 一种新的 AI 软件做法 过去做 AI 应用,要先搭工作流:拖节点、连线、写死每一步的提示词、接一堆 API。流程搭成什么样,AI 就只能做到什么样。 SoloMCN 反过来:零搭建工作流,直接操纵 Claude。 工作台本身只做两件事:给 Claude 递工具(读写账号和素材、截网页、发布到各平台),给你留看得见、拍得了板的地方。真正干活的是 Claude Code:它自己上网查资料、自己写代码做视频、自己检查画面、出错了自己修。 真实发生过的 做这个 README 里的演示视频时: 配音额度用完了:托管配音的免费额度是 0。没有人写过这个分支,Claude 自己装好本地语音,给鹦鹉、乌龟、狮子三个角色各配了一个声音,把片子做完。 一句话返工:我们觉得配音听不清,在工作台里写了一句「配音听不懂,换成系统中文语音」。Claude 只重配了声音、重新对齐字幕、重新渲染,画面一帧没动,10 分钟交回新版。 自己做画面:角色是它画的原创矢量图;中间穿插的 GitHub 页面、新闻报道、学者博客,是它调研时自己截下来的真网页,还加了荧光笔高亮和红圈。 这些都不是预先写好的流程,是 Claude 当场想出来的。 从热点到发布,全程交给 Claude 每个箭头都是一次 Claude Code 运行,页面上实时看它每一步在做什么,跑到一半还能插话。你只在三处拍板:做哪个选题、成片行

ai-agentai-videoautomationbilibiliclaudeclaude-codecontent-creationdouyinhyperframesmcn

Quick Facts

Stars53
Forks13
LanguageJavaScript
CategoryAgent Tool
LicenseMIT
Quality Score61.2107313000719/100
Open Issues1
Last Updated2026-10-12
Created2026-10-09
Platformsclaude-code, node
Est. Tokens~14k

SoloMCN alternative? Top 6 similar tools

Looking for a SoloMCN alternative? If you're comparing SoloMCN with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • content-pipeline by OrangeViolin · ⭐ 213

    AI-powered content production pipeline for creators. One prompt → multi-platform publishing. Claude Code Skill

  • kinocut by KyaniteLabs · ⭐ 202

    Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and

  • socialclaw by BlockRunAI · ⭐ 130

    Grow your X/Twitter to 5M+ views in 3 months — trend detection, audience insights, engagement targets, KOL dis

  • tweetclaw by Xquik-dev · ⭐ 94

    OpenClaw plugin for Twitter search, follower exports, monitoring & approved X actions. Not affiliated with X C

  • narrator-ai-cli-skill by GridLtd-ProductDev · ⭐ 79

    AI Agent skill for narrator-ai-cli — CLI client for Narrator AI video narration API

  • mcp-video by KyaniteLabs · ⭐ 72

    Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is SoloMCN?

SoloMCN is 把 Claude Code 变成你的短视频团队:不搭工作流,直接让 Claude 干活,从国内热榜、推特热帖到抖音、小红书、B站、YouTube、推特发布。Turn Claude Code into your short-video team — no workflows, from trends and X posts to publishing.. It is categorized as a Agent Tool with 53 GitHub stars.

What programming language is SoloMCN written in?

SoloMCN is primarily written in JavaScript. It covers topics such as ai-agent, ai-video, automation.

How do I install or use SoloMCN?

You can find installation instructions and usage details in the SoloMCN GitHub repository at github.com/ymybxx/SoloMCN. The project has 53 stars and 13 forks, indicating an active community.

What license does SoloMCN use?

SoloMCN is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to SoloMCN?

The top alternatives to SoloMCN on Agent Skills Hub include content-pipeline, kinocut, socialclaw. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools