by safe-agentic-world · MCP Server · ★ 19
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Claude Code Hooks, Subagents & Statusline
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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.
One of 12 tools we ran end to end on the same task for our Claude Code Hooks, Subagents & Statusline page (2026-10-10).
Our pick (Install this one): Stopped 7 of 8 risky actions by itself, with or without Claude Code's prompts, and never interrupted the four ordinary ones. It missed chmod -R 777. It is a policy engine, so expect to read its profile.
Result: A policy engine with a default profile: it denies secret access and asks before deletes, pushes and anything outside the project. · stopped 7 of 8 risky actions with prompts skipped · with prompts kept: 7 of 8 stopped, 4 of 4 ordinary actions through without a prompt
| Stars | 19 |
| Forks | 1 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-27 |
| Created | 2026-02-25 |
| Platforms | claude-code, cli, codex, go, mcp |
| Est. Tokens | ~19k |
Deny-wins policy hook for Claude Code and Codex. Checks every shell, file, and fetch call against rules you keep in Git, holds under --dangerously-skip-permissions, refuses commands it cannot parse, and keeps a hash-linked audit log.
These tools work well together with nomos for enhanced workflows:
Looking for a nomos alternative? If you're comparing nomos 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.
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Stop your AI agent from shipping insecure IaC. ops0 CLI sits between Claude Code, Codex or Gemini and your clo
The open-source AI agent control plane and software factory: govern every tool and model call.
See what your AI coding agents are doing and what they cost. Live activity map, tokens, cost, context and quot
The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in co
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: