by KongFangXun · MCP Server · ★ 54
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/KongFangXun/sofagent.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 54 |
| Forks | 9 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65/100 |
| Open Issues | 9 |
| Last Updated | 2026-10-22 |
| Created | 2026-06-18 |
| Platforms | mcp, node |
| Est. Tokens | ~17k |
sofagent 中文 | English sofa + agent = 沙发特工——希望有一天，我们能躺在沙发上，Agent 就把活干完了。 v0.91 · 2026-06-24 📄 License：MIT。代码、文档、模板——随便用，保留版权声明就行。 我叫孔放勋，一个不是很懂代码的产品经理。所有设计决策来自大半年的真实使用经验，文档由 DeepSeek V4 Pro 和 GLM-5.2 配合生成。欢迎大佬进来改。 这个项目是怎么做出来的？一句话：疯狂烧 token，大力出奇迹。 我代码写得很糟糕，所以换了一种方式——把 sofagent 自己的铁律反过来用在自己身上。DeepSeek 写代码，GLM 审设计，两个模型在 loop 里互相校验，我坐在中间当产品经理：定约束、看产出、做终审。相当于请了两个 AI 工程师加一个 AI QA，代码在「烧 token...
These tools work well together with sofagent for enhanced workflows:
Looking for a sofagent alternative? If you're comparing sofagent with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, eve
Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and
You.com skills and plugins for web search, content extraction, research, finance, and integration discovery, h
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
The open-source AI agent control plane and software factory: govern every tool and model call.
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: