AI导哈

代码审查MCP服务

为 Claude Code 提供 AI 驱动的代码审查MCP服务，直接在编辑器中自动化复杂度分析、反模式检测、安全审查、测试生成与性能优化，适用于使用 Claude Code 的开发者与团队。

  • by rhkiswani
  • 本地部署
  • 更新于
在 GitHub 查看 OyaAIProd/truss-code-review-mcp

使用说明

TRUSS Code Review MCP Server

AI-powered code review tools for Claude Code. Automated complexity analysis, anti-pattern detection, security review, and optimization — directly in your editor.

Quick Start

{
  "mcpServers": {
    "code-review": {
      "command": "npx",
      "args": ["-y", "truss-code-review-mcp"]
    }
  }
}

Tools

Free Tier (no key needed)

Tool Description
review_diff Analyze a git diff for common issues (debug statements, TODOs, secrets, commented-out code)
check_complexity Calculate cyclomatic complexity of functions (JS/TS, Python, Go)
detect_antipatterns Detect language-specific anti-patterns with fix suggestions

Pro Tier ($25/mo)

Requires TRUSS_LICENSE_KEY + your own ANTHROPIC_API_KEY or OPENAI_API_KEY.

Tool Description
deep_review AI-powered comprehensive code review with scored findings
suggest_tests Generate complete, runnable test files
explain_code Generate documentation, docstrings, and data flow analysis
security_review OWASP-based security analysis with CWE references
optimize_code Performance optimization with before/after code

Configuration

# Free tier — just install, no config needed

# Pro tier
export TRUSS_LICENSE_KEY="truss_..."
export ANTHROPIC_API_KEY="sk-ant-..."  # or OPENAI_API_KEY

Anti-Pattern Coverage

JavaScript/TypeScript: var usage, loose equality (==), any type, eval(), innerHTML, sync I/O, @ts-ignore, console statements, callback hell, magic numbers

Python: bare except, mutable default args, wildcard imports, global statement, string concatenation in loops, hardcoded credentials, type() comparison, debug prints

Go: ignored errors, goroutine leaks, mutex without defer, string([]byte) in loops, panic() in library code, init() functions, naked returns, error wrapping with %s

License

MIT

A2A Discovery

This server publishes a Google A2A Protocol Agent Card, making it discoverable by any A2A-compatible agent framework (LangGraph, CrewAI, Google ADK, AutoGen, and others).

Agent Card: agent-card.json

The agent card describes this server's skills, capabilities, input/output modalities, and authentication requirements in a machine-readable format. A2A clients can use it to discover and invoke tools automatically without manual configuration.

# Fetch the agent card
curl https://raw.githubusercontent.com/claw-factory/truss-code-review-mcp/main/agent-card.json

相关 MCP