by liyana31811 · MCP Server · ★ 74
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Let ChatGPT use Codex's local toolbox, then call Codex only when needed.
| Stars | 74 |
| Forks | 14 |
| Language | JavaScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 55.4814608008527/100 |
| Open Issues | 4 |
| Last Updated | 2026-09-05 |
| Created | 2026-08-15 |
| Platforms | codex, mcp, node |
| Est. Tokens | ~13k |
Looking for a Codexless alternative? If you're comparing Codexless 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.
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
MCP Server & Config Manager for 14 AI Clients — Cursor, VS Code, Claude Code, Gemini CLI, Windsurf, Zed, TRAE,
MCP Fusion - The framework for AI-native MCP servers.
All-in-one MCP server that can connect your AI agents to any native endpoint, powered by UTCP
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular mcp server tools:
Codexless is Let ChatGPT use Codex's local toolbox, then call Codex only when needed.. It is categorized as a MCP Server with 74 GitHub stars.
Codexless is primarily written in JavaScript. It covers topics such as chatgpt, codex, developer-tools.
You can find installation instructions and usage details in the Codexless GitHub repository at github.com/liyana31811/Codexless. The project has 74 stars and 14 forks, indicating an active community.
Codexless is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Codexless on Agent Skills Hub include ClaudeR, deepcontext-mcp, mcp-dock. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: