by genai-io · MCP Server · ★ 146
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
go install github.com/genai-io/san/cmd/san@latest
git clone https://github.com/genai-io/san.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 | 146 |
| Forks | 35 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 71/100 |
| Open Issues | 6 |
| Last Updated | 2026-11-04 |
| Created | 2024-09-05 |
| Platforms | claude-code, cli, go, mcp |
| Est. Tokens | ~18k |
< SAN ✦ /> Open-source unified runtime for specialized AI agents — in the terminal English · 简体中文 ▶ Watch the animated intro Open the full-quality vers
These tools work well together with san for enhanced workflows:
Looking for a san alternative? If you're comparing san 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.
TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
A desktop app for coding with agents. Each thread is a real terminal running the agent you already use.
Process manager for AI agents (and humans)
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines
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: