cuga-agent — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 cuga-project · MCP Server · ★ 879

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

🔒 Is cuga-agent safe to install? View the security audit →

About cuga-agent

CUGA: Configurable Generalist Agent — Agent Harness for the Enterprise Start with a generalist. Customize for your domain. Deploy faster! Building a domain-specific enterprise agent from scratch is complex and requires significant effort: agent and tool orchestration, planning logic, safety and alignment policies, evaluation for performance/cost tradeoffs and ongoing improvements. CUGA is a state-of-the-art generalist agent designed with enterprise needs in mind, so you can focus on configuring your domain tools, policies and workflow. []() [](https:

coding-agentcomputer-useenterprisegeneralist-agentguardrailsharnessknowledgemcppoliciessandbox

Quick Facts

Stars879
Forks156
LanguagePython
CategoryMCP Server
Quality Score72.442256456082/100
Open Issues180
Last Updated2026-09-17
Created2025-09-11
Platformsbrowser, mcp, python
Est. Tokens~24k

Compatible Skills

These tools work well together with cuga-agent for enhanced workflows:

  • open-computer-use — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • mac_computer_use — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • os-ai-computer-use — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (55%)
  • Toolathlon — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)
  • claude-computer-use-macos — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

cuga-agent alternative? Top 6 similar tools

Looking for a cuga-agent alternative? If you're comparing cuga-agent 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-cowork by OpenCoworkAI · ⭐ 2.1k

    Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — w

  • agent-kernel by yaalalabs · ⭐ 191

    The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI

  • TuriX-CUA by TurixAI · ⭐ 3.2k

    This is the official website for TuriX Computer-use-Agent

  • cocoindex-code by cocoindex-io · ⭐ 2.7k

    A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficie

  • ghost-os by ghostwright · ⭐ 1.7k

    Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.

  • llmgateway by theopenco · ⭐ 1.7k

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is cuga-agent?

cuga-agent is CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aw. It is categorized as a MCP Server with 879 GitHub stars.

What programming language is cuga-agent written in?

cuga-agent is primarily written in Python. It covers topics such as coding-agent, computer-use, enterprise.

How do I install or use cuga-agent?

You can find installation instructions and usage details in the cuga-agent GitHub repository at github.com/cuga-project/cuga-agent. The project has 879 stars and 156 forks, indicating an active community.

What are the best alternatives to cuga-agent?

The top alternatives to cuga-agent on Agent Skills Hub include open-cowork, agent-kernel, TuriX-CUA. 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