by maksimzayats · MCP Server · ★ 59
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: OpenAI Codex Skills
uv add acodex
uv add "acodex[structured-output]"Taken from the project's README on GitHub.
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.
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 | 59 |
| Forks | 1 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70/100 |
| Last Updated | 2026-11-06 |
| Created | 2026-02-14 |
| Platforms | cli, codex, mcp, python |
| Est. Tokens | ~14k |
acodex acodex is a fast, typed Python SDK for Codex CLI workflows (sync/async, streaming, structured output, images, safety controls), and API parity with the TypeScript SDK. What is acodex? acodex spawns the CLI and exchanges JSONL events over stdin/stdout so you can run agent threads from Python with a fully typed surface: sync + async clients, streaming events, structured output, image inputs,...
Looking for a acodex alternative? If you're comparing acodex 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.
Typed Python Runtime API for Claude Agent OpenAI Codex and Google Antigravity SDKs
Lightweight agent orchestration dev tool that lives in your repo
Cross-platform desktop notifications for Claude Code, Codex, and Gemini CLI. Install via Homebrew, npm, or scr
MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface
Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image
Full-text search and resume for Claude/Codex conversations
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: