aigis — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 killertcell428 · MCP Server · ★ 54

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is aigis safe to install? View the security audit →

About aigis

Aigis The open-source trust layer for bringing Claude Code (and other autonomous AI agents) to work — with your security team's approval. Your company won't approve Claude Code? The blocker is rarely the model — it's the missing answer to "what can it run, and where's the audit trail?" Aigis is the layer that answers it: deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack — on any Claude Code plan. Independent OSS, Apache-2.0, zero runtime dependencies. pip install pyaigis. From pip install to IT approval in 3 commands wires PreToolUse hooks into Claude Code so every Bash/Edit/Write/WebFetch is scanned before it runs, and records every decision to an append-only audit log. A tamper-evident signed log (HMAC-SHA256 + hash chain) ships in the box — prove log integrity anytime with . reads your live local config and writes an approval pack — executive summary

ai-agentai-securityaudit-logclaude-codecompliancecybersecurityfirewallguardrailsjailbreak-detectionllm

Quick Facts

Stars54
Forks8
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score70.2342972546681/100
Open Issues9
Last Updated2026-09-02
Created2026-04-11
Platformsclaude-code, mcp, python
Est. Tokens~17k

aigis alternative? Top 6 similar tools

Looking for a aigis alternative? If you're comparing aigis 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.

  • panguard-ai by panguard-ai · ⭐ 63

    Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat inte

  • agent-audit by HeadyZhang · ⭐ 229

    Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mappe

  • pfsense-mcp-server by gensecaihq · ⭐ 91

    Model Context Protocol (MCP) server for pfSense firewall management. Control firewall rules, VPNs, DNS, DHCP a

  • deterministic-agent-control-protocol by elliot35 · ⭐ 89

    Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT

  • Wazuh-MCP-Server by gensecaihq · ⭐ 232

    Production-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability

  • agent-security-scanner-mcp by sinewaveai · ⭐ 121

    Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is aigis?

aigis is Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.. It is categorized as a MCP Server with 54 GitHub stars.

What programming language is aigis written in?

aigis is primarily written in Python. It covers topics such as ai-agent, ai-security, audit-log.

How do I install or use aigis?

You can find installation instructions and usage details in the aigis GitHub repository at github.com/killertcell428/aigis. The project has 54 stars and 8 forks, indicating an active community.

What license does aigis use?

aigis is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to aigis?

The top alternatives to aigis on Agent Skills Hub include panguard-ai, agent-audit, pfsense-mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools