by sonirico · MCP Server · ★ 107
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
docker run -it --rm -v /tmp/mcp-workspace:/tmp/mcp-workspace sonirico/mcp-shell:latest
git clone https://github.com/sonirico/mcp-shell && cd mcp-shellTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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 | 107 |
| Forks | 20 |
| Language | Go |
| Category | MCP Server |
| License | GPL-3.0 |
| Quality Score | 75/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-25 |
| Created | 2025-05-24 |
| Platforms | go, mcp |
| Est. Tokens | ~16k |
mcp-shell MCP server that runs shell commands. Your LLM gets a tool; you get control over what runs and how. Built on mark3labs/mcp-go. Written in Go. Run it Docker (easiest): From source: Configure it Security is off by default.
Looking for a mcp-shell alternative? If you're comparing mcp-shell 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.
mcpc is a CLI client for MCP. It supports persistent sessions, stdio/HTTP, OAuth 2.1, JSON output for code mod
Authentication, analytics, and prompt visibility for MCP servers with zero code changes. Supports OAuth2.1, DC
AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers
🔐 SSH MCP Tool - AI-powered SSH management through MCP protocol | 基于MCP协议的SSH工具，为AI提供SSH远程操作能力
Turn MCP servers into composable CLIs.
MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime de
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: