by veithly · MCP Server · ★ 79
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/veithly/vibeshell.gitTaken 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 | 79 |
| Forks | 10 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70/100 |
| Last Updated | 2026-09-07 |
| Created | 2026-02-13 |
| Platforms | claude-code, cli, codex, mcp, rust |
| Est. Tokens | ~24k |
VibeShell An AI-native SSH, SFTP, tunnel, and local terminal workspace for developers who ship from the command line. Screenshots · Why It Exists · Features · AI Agents · Install · Build VibeShell is a modern desktop terminal for people and AI agents working on the same machines.
Looking for a vibeshell alternative? If you're comparing vibeshell 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.
Octo Terminal — The ultimate vibe coding terminal. AI-powered IDE with Claude, Codex, Ollama built-in. Termina
Terminal Director. One lightweight app, eight features, your whole dev workflow in a single window.
A professional tool to safely and efficiently apply LLM-suggested code changes to your local codebase in a con
A desktop companion app for AI coding tools. Browse Claude Code chat history, manage configurations, commands,
Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support
AI powered SSH, SFTP, telnet and Windows RDP in a single window, with integrations for Claude Code, Codex and
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: