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 leonardsellem · MCP Server · ★ 160
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-subagents-mcp safe to install? View the security audit →
codex-subagents-mcp Status: Archived. This repo is no longer maintained. I’m restarting this project from scratch with a new approach in: https://github.com/leonardsellem/codex-specialized-subagents File‑based sub‑agents for Codex CLI. One MCP tool. Zero fluff. Auditable: agents are files reviewed in PRs CI‑friendly: , Safer ops: temp workdirs, quiet stdout, git worktree isolation Claude‑style sub‑agents for Codex CLI via a tiny MCP server. Each call spins up a clean context in a temp workdir, injects a persona via , and runs to preserve isolated state. Quickstart Prereqs: Node.js = 18, npm, Codex CLI installed and on PATH. Install deps and build: Start server (manual run): Tools exposed by this server: Primary: Support: , Agents directory discovery (in order): arg, env, then defaults , , di
| Stars | 160 |
| Forks | 24 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 71.2602118366983/100 |
| Open Issues | 3 |
| Last Updated | 2025-12-29 |
| Created | 2025-08-27 |
| Platforms | claude-code, cli, codex, mcp, node |
| Est. Tokens | ~11k |
These tools work well together with codex-subagents-mcp for enhanced workflows:
Explore other popular mcp server tools:
codex-subagents-mcp is Claude-style sub-agents (reviewer, debugger, security) for Codex CLI via a tiny MCP server. Each call spins up a clean context in a temp workdir, injects a persona via AGENTS.md, and runs codex exec -. It is categorized as a MCP Server with 160 GitHub stars.
codex-subagents-mcp is primarily written in JavaScript.
You can find installation instructions and usage details in the codex-subagents-mcp GitHub repository at github.com/leonardsellem/codex-subagents-mcp. The project has 160 stars and 24 forks, indicating an active community.
codex-subagents-mcp is released under the MIT license, making it free to use and modify according to the license terms.
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: