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 genai-io · MCP Server · ★ 78
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is san safe to install? View the security audit →
< 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
| Stars | 78 |
| Forks | 33 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 70.3191807353506/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-19 |
| Created | 2024-09-05 |
| Platforms | claude-code, cli, go, mcp |
| Est. Tokens | ~18k |
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.
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)
Process manager for AI agents (and humans)
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, backgro
Explore other popular mcp server tools:
san is Lean context, native speed, open all the way down — an open-source terminal agent runtime. One 12 MB Go binary, zero runtime deps.. It is categorized as a MCP Server with 78 GitHub stars.
san is primarily written in Go. It covers topics such as agent-harness, ai-agents, claude-code.
You can find installation instructions and usage details in the san GitHub repository at github.com/genai-io/san. The project has 78 stars and 33 forks, indicating an active community.
san is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to san on Agent Skills Hub include maestro, toktrack, gob. 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: