What is Argus

Argus is a Model Context Protocol (MCP) server designed for analyzing GitLab repositories and performing security assessments across various programming languages.

Use cases

Use cases for Argus include analyzing the structure of code repositories, performing security scans on codebases, assessing code quality across multiple languages, and visualizing repository structures for better understanding.

How to use

To use Argus, install it via ‘uvx argus’ after ensuring prerequisites like Python 3.8+, Git, and libmagic are met. Utilize basic MCP commands to analyze repository structure, perform code quality analysis, conduct security scans, and compare Git changes.

Key features

Key features of Argus include multi-language support for Go, Java, Python, and JavaScript/TypeScript, integrated security scanning with Trivy, Git operations for branch management and commit history analysis, and automatic language detection.

Where to use

Argus can be used in software development environments, particularly for teams utilizing GitLab for version control and requiring security assessments and code quality checks.

Argus - Repository Analysis and Security Assessment Tool

A powerful Model Context Protocol (MCP) tool for analyzing code repositories, performing security scans, and assessing code quality across multiple programming languages.

Features

• Multi-Language Support

  • Go: gocyclo, golangci-lint analysis
  • Java: PMD static analysis
  • Python: Pylint, Bandit security checks
  • JavaScript/TypeScript: ESLint analysis
  • Automatic language detection

• Security Scanning

  • Integrated Trivy vulnerability scanner
  • Comprehensive security reports
  • Support for multiple branches

• Git Operations

  • Branch enumeration and management
  • Commit history analysis
  • Diff comparisons
  • Repository structure visualization

Installation

Prerequisites

• Python 3.8+
• Git
• libmagic (system dependency)

System Dependencies

macOS

brew install libmagic

Linux (Ubuntu/Debian)

sudo apt-get update
sudo apt-get install -y libmagic1

Installation via uv

uvx argus

Usage

Basic MCP Commands

# Analyze repository structure
analyze_repository_structure(
    repo_url="https://gitlab.com/user/repo",
    gitlab_credentials={"api_key": "your-token"},  # Optional
    branch="main"  # Optional
)

# Perform code quality analysis
analyze_code_quality(
    repo_url="https://gitlab.com/user/repo",
    language="python"  # Optional, will auto-detect if not specified
)

# Security scan
security_scan_repository(
    repo_url="https://gitlab.com/user/repo",
    scan_type="trivy"
)

# Compare changes
compare_git_changes(
    repo_url="https://gitlab.com/user/repo",
    source="feature-branch",
    target="main"
)

# Security scan repository
security_scan_repository(
    repo_url="https://gitlab.com/user/repo",
    scan_type="trivy"
)

### MCP Configuration

```json
{
    "command": "uvx",
    "args": [
        "--from",
        "git+https://github.com/athapong/argus",
        "argus"
    ],
    "alwaysAllow": [
        "get_commit_history",
        "enumerate_branches",
        "compare_git_changes",
        "analyze_code_quality",
        "security_scan_repository"  
    ],
    "timeout": 300
}

Supported Analysis Tools

Environment Variables

• SKIP_SYSTEM_CHECK: Set to any value to skip system dependency checks
• PATH: Automatically updated for tool installations

Error Handling

The tool provides detailed error messages and graceful fallbacks:

• Dependency installation failures show warnings instead of errors
• Language detection falls back to specified language if auto-detection fails
• Tool execution errors are captured in the response structure

License

MIT License

Contributing

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Create a new Pull Request