Flagged: sudo usage, spawns subprocesses. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by instavm · MCP Server · ★ 882
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is coderunner safe to install? View the security audit →
CodeRunner: A local sandbox for your AI agents CodeRunner helps you sandbox your AI agents and its actions inside a sandbox. Key use case: You can run multiple Claude Code or AI agents in our sandbox without any fear of data loss and exfilteration. Quick Start Prerequisites: Mac with macOS and Apple Silicon (M1/M2/M3/M4), Python 3.10+ Stop and resume Stop the sandbox when you are done: Resume the same sandbox later, preserving uploads, kernels, and installed packages: To start over with a clean sandbox, delete the container and run the installer again: Run Claude Code inside a Sandbox (if not already done) Other Inte
| Stars | 882 |
| Forks | 41 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.3964477826597/100 |
| Open Issues | 9 |
| Last Updated | 2026-08-13 |
| Created | 2025-06-23 |
| Platforms | claude-code, cli, gemini, mcp, python |
| Est. Tokens | ~15k |
Looking for a coderunner alternative? If you're comparing coderunner 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.
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - th
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
Explore other popular mcp server tools:
coderunner is A local sandbox for your AI agents. It is categorized as a MCP Server with 882 GitHub stars.
coderunner is primarily written in Python. It covers topics such as anthropic, apple, apple-container.
You can find installation instructions and usage details in the coderunner GitHub repository at github.com/instavm/coderunner. The project has 882 stars and 41 forks, indicating an active community.
coderunner is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to coderunner on Agent Skills Hub include Unity-MCP, awesome-llm-skills, vllm-mlx. 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: