dykeruv/argus-mcp

View on GitHub by @dykeruv

🔍 Enhance code quality with Argus MCP, an AI-driven code review server using a Zero-Trust model for safe and efficient development.

What's novel

🔍 Enhance code quality with Argus MCP, an AI-driven code review server using a Zero-Trust model for safe and efficient development.

Code Analysis

9 files read · 3 rounds

An MCP server that wraps LLM API calls (GLM, Gemini, MiniMax) with retry/fallback logic, a basic in-memory cache, and a context optimizer that strips comments/imports from code before sending it to the model for code review.

Strengths

The context optimizer has genuine AST-based logic for Python chunking and import compression, and the retry/fallback chain with exponential backoff is reasonably well-implemented with proper error categorization and user-facing diagnostics.

Weaknesses

The README is completely misleading (describes a GUI desktop app with .exe/.dmg downloads and .NET requirements for what is a Python MCP server), there are zero real tests (the test file is a 5-line placeholder), and the core value is thin — it's essentially a prompt template wrapper around existing LLM APIs with no proprietary review logic.

Score Breakdown

Innovation

4 (25%)

Craft

45 (35%)

Traction

6 (15%)

Scope

28 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+0

Concept Novelty+1

Craft

Ci+0

Tests-1

Polish+2

Releases+0

Has License+5

Code Quality+15

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+5

Languages+3

Subsystems+5

Bloat Penalty+0

Completeness+7

Contributors+6

Authored Files+8

Readme Code Match+3

Architecture Depth+3

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

MIT