Skip to main content
Glama

šŸš€ Code Quality MCP Server

Hybrid Code Quality Analysis - Combines logic-based checks with AI-powered deep analysis

MCP (Model Context Protocol) system for code quality analysis. Supports two modes:

  • ⚔ Fast Mode: Quick logic-based checks

  • šŸ¤– Deep Mode: AI-powered deep analysis (Claude)


šŸ”§ Installation

npm install
npm run build

Related MCP server: Tech Debt MCP Server

ā–¶ļø Running the Server

Option 1: Direct Run

npm start

Option 2: Via Claude Desktop

Add to ~/.config/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "code-quality": {
      "command": "node",
      "args": ["/absolute/path/to/code-quality-mcp/dist/index.js"]
    }
  }
}

šŸ“š API Tools

šŸ” Analysis Tools

1. check_quality - Full Code Quality Check

{
  "tool": "check_quality",
  "arguments": {
    "projectPath": ".",
    "deepAnalysis": false,     // true = AI mode
    "checkUnusedCode": true,
    "checkComplexity": false,  // requires AI
    "checkSecurity": false,    // requires AI
    "page": 1,                 // pagination
    "pageSize": 50             // items per page
  }
}

Returns: Complete list of issues with pagination


2. get_smart_summary - Smart Summary ⭐

Instead of 500 issues, get a focused summary:

{
  "tool": "get_smart_summary",
  "arguments": {
    "projectPath": "."
  }
}

Returns:

šŸ“Š Score: 68/100
šŸ“ˆ Issues: 500 (120 critical)
ā±ļø Fix Time: 2 days

šŸ”„ Top Problems:
  • unused-code: 300 (60%)
  • security: 50 (10%)

šŸ“ Hotspot Files:
  šŸ”“ UserService.ts - 45 issues

3. get_quick_wins - Quick Wins ⚔

Get only actions that provide maximum impact in minimum time:

{
  "tool": "get_quick_wins",
  "arguments": {
    "projectPath": "."
  }
}

Returns:

⚔ Quick Wins:
1. Remove 50 unused vars (10 min) → +15 points
2. Fix 30 console.log (5 min) → +8 points
3. Translate Hebrew comments (15 min) → +5 points

Total: 30 minutes → +28 points!

4. get_trends - Progress Tracking šŸ“ˆ

See how code quality improves over time:

{
  "tool": "get_trends",
  "arguments": {
    "projectPath": "."
  }
}

Returns:

šŸ“ˆ Trends:
  āœ… Score: 45 → 68 (+23)
  āœ… Fixed: 120 issues
  āš ļø New: 15 issues

Improving:
  • unused-code: 300 → 180 (-120)
  • security: 10 → 5 (-5)

Degrading:
  • code-style: 50 → 65 (+15)

šŸ”§ Other Tools

5. analyze_project - Project Type Detection

{
  "tool": "analyze_project",
  "arguments": {
    "projectPath": ".",
    "deep": true
  }
}

6. get_recommendations - Quick Recommendations

{
  "tool": "get_recommendations",
  "arguments": {
    "projectPath": ".",
    "language": "en"  // or "he" for Hebrew
  }
}

⚔ Fast vs Deep Mode

Feature

Fast Mode

Deep Mode

Speed

~20ms

~1000ms

Cost

Free

API calls

Accuracy

Good

Excellent

AI insights

āŒ

āœ…

When to use Fast Mode:

  • During development

  • Before commits

  • In CI/CD pipelines

When to use Deep Mode:

  • Before Pull Requests

  • Code reviews

  • Security audits


šŸ“– Examples


šŸŒ Supported Platforms

  • Node.js / TypeScript

  • React / React Native

  • Next.js / NestJS

  • Firebase / AWS Amplify

  • Java / .NET / Angular


šŸš€ Key Features

āœ… Smart Ignore Patterns - Automatically skips:

  • node_modules, build, dist, .git

  • React Native: android/gradle, ios/Pods, native build folders

  • Only scans your code, not auto-generated files

āœ… Pagination - Handle large projects with many issues

āœ… Smart Summaries - Get actionable insights instead of overwhelming lists

āœ… Quick Wins - Find high-impact, low-effort fixes

āœ… Trend Tracking - Monitor code quality improvements over time


Built with ā¤ļø using MCP and Claude

Available Tools

6 tools
analyze_projectC

Analyze project type and code quality

Inputs: projectPath (required), deep.

check_qualityC

Check code quality based on project type. Supports both fast (logic-based) and deep (AI-powered) analysis modes.

Inputs: projectPath (required), page, pageSize, aiEnabled, +5 more.

get_quick_winsB

Get high-impact, low-effort fixes to quickly improve code quality score

Inputs: projectPath (required).

get_recommendationsC

Get code quality recommendations

Inputs: projectPath (required), language.

get_smart_summaryB

Get a concise, actionable summary of code quality instead of full issue list

Inputs: projectPath (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 6 tools

    Disambiguation3/5

    analyze_project and check_quality overlap in purpose, both analyzing project type and quality. The get_recommendations, get_smart_summary, and get_quick_wins tools are related but distinct in output style, so disambiguation is moderate.

    Naming Consistency5/5

    All tool names consistently follow a verb_noun pattern (analyze_project, check_quality, get_recommendations, etc.). The use of get_ for most retrieval functions is uniform and predictable.

    Tool Count5/5

    Six tools is within the ideal 3-15 range for a focused code-quality server. Each tool addresses a specific aspect of the domain without bloat.

    Completeness4/5

    The tool set covers analysis, quality checking, recommendations, summaries, quick wins, and trends, providing a comprehensive view of code quality. Missing a raw issue list or fix application is a minor gap, but agents can work around it via the existing tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides comprehensive codebase analysis including project structure evaluation, cross-language duplicate detection, microservices validation, and configuration optimization with AI-powered pattern learning that generates actionable improvement reports.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      A server for analyzing technical debt across multiple programming languages, integrating with MCP-compatible tools to detect code quality issues and provide prioritized recommendations.
      16
      73 npm
      7
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      An MCP server that provides local code quality analysis for AI coding assistants, supporting file analysis, git diff review, and full project scanning with quality scoring.
      5
      38 PyPI
      3
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      AI-powered code quality analysis that detects security issues, bugs, code smells, and performance problems across multiple languages.
      4
      -