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 raullenchai · MCP Server · ★ 156
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vnsh safe to install? View the security audit →
vnsh The Ephemeral Dropbox for AI Website • Quick Start • How It Works • Self-Hosting • API What is vnsh? Stop pasting walls of text into Claude. Pipe your logs, diffs, and images into a
| Stars | 156 |
| Forks | 24 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 77.5649871428724/100 |
| Open Issues | 18 |
| Last Updated | 2026-09-06 |
| Created | 2026-01-24 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~17k |
Looking for a vnsh alternative? If you're comparing vnsh 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.
Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Close the lid and walk away — every window, desktop and terminal on your machines, live in any browser. E2E-en
Explore other popular mcp server tools:
vnsh is One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.. It is categorized as a MCP Server with 156 GitHub stars.
vnsh is primarily written in TypeScript. It covers topics such as ai-agents, claude, claude-code.
You can find installation instructions and usage details in the vnsh GitHub repository at github.com/raullenchai/vnsh. The project has 156 stars and 24 forks, indicating an active community.
vnsh is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to vnsh on Agent Skills Hub include TaskWing, Overture, agnix. 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: