by miuuyy · MCP Server · ★ 15.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 15,312 |
| Forks | 1,211 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69/100 |
| Open Issues | 12 |
| Last Updated | 2026-10-30 |
| Created | 2026-07-26 |
| Platforms | browser, codex, mcp, node |
| Est. Tokens | ~16k |
ChatGPT Web for Codex Use ChatGPT Web (including Pro) as native Codex models. Change the model tier, save your workflow. English · 简体中文 Pick ChatGPT Web — Instant, Medium, High, Extra High, or Pro in Codex's native model picker.
These tools work well together with codex-chatgpt-web for enhanced workflows:
Looking for a codex-chatgpt-web alternative? If you're comparing codex-chatgpt-web 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.
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/G
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Pr
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature,
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
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: