Adrian — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 secureagentics · MCP Server · ★ 564

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

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

About Adrian

Open-source runtime security monitoring and control for AI agents. Adrian is an open-source, AARM-aligned runtime security monitoring and control engine for AI agents. I

aarmagent-securityagentic-aiagentic-securityagentsaiai-agentsai-governanceai-securitylangchain

Quick Facts

Stars564
Forks93
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score66.6401288468542/100
Open Issues6
Last Updated2026-09-15
Created2026-05-11
Platformsmcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with Adrian for enhanced workflows:

  • openclaw-skills-security — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (62%)
  • prompt-guard — semantic(0.46)+complementary+same_lang+similar_pop+shared_platform (61%)
  • allama — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)

Adrian alternative? Top 6 similar tools

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

  • nono by always-further · ⭐ 2.2k

    nono - a capability-based, multiplexing sandbox tool, built for developers - lift'n'shift seamless path to pro

  • node9-proxy by node9-ai · ⭐ 214

    The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for

  • DeepMCPAgent by cryxnet · ⭐ 806

    Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.

  • hol-guard by hashgraph-online · ⭐ 634

    Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, M

  • awesome-MLSecOps by RiccardoBiosas · ⭐ 465

    A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML d

  • agentseal by AgentSeal · ⭐ 156

    Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Adrian?

Adrian is Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.. It is categorized as a MCP Server with 564 GitHub stars.

What programming language is Adrian written in?

Adrian is primarily written in Python. It covers topics such as aarm, agent-security, agentic-ai.

How do I install or use Adrian?

You can find installation instructions and usage details in the Adrian GitHub repository at github.com/secureagentics/Adrian. The project has 564 stars and 93 forks, indicating an active community.

What license does Adrian use?

Adrian 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 Adrian?

The top alternatives to Adrian on Agent Skills Hub include nono, node9-proxy, DeepMCPAgent. 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