Dependency MCP

🚀 Dependency MCP Server

A Model Context Protocol (MCP) server that analyzes codebases to generate dependency graphs and architectural insights. This server helps understand code structures, dependencies, and architectural patterns across multiple programming languages.

🚀 Quick Start

The Dependency MCP Server is designed to analyze codebases and provide valuable insights into dependencies and architecture. Follow the steps below to get started.

✨ Features

• Multi-language Support: Analyze dependencies in languages such as TypeScript, JavaScript, C#, and Python.
• Dependency Graph Generation: Generate detailed dependency graphs in JSON or DOT format.
• Architectural Analysis: Infer architectural layers and validate rules.
• File Metadata: Extract import, export, and other file information.
• Scoring System: Evaluate the codebase's compliance with architectural rules and patterns.

📦 Installation

1. Clone the repository.
2. Install the dependencies:

npm install

3. Build the project:

npm run build

📚 Documentation

Configuration

Add the following to the MCP settings file (usually located at ~/.config/cline/mcp_settings.json or a similar path):

{
  "mcpServers": {
    "DependencyMCP": {
      "command": "node",
      "args": ["path/to/dependency-mcp/dist/index.js"],
      "env": {
        "MAX_LINES_TO_READ": "1000",
        "CACHE_DIR": "path/to/dependency-mcp/.dependency-cache",
        "CACHE_TTL": "3600000"
      }
    }
  }
}

Environment Variables

• MAX_LINES_TO_READ: Maximum number of lines to read per file (default: 1000).
• CACHE_DIR: Directory to store dependency cache (default: .dependency-cache).
• CACHE_TTL: Cache expiration time in milliseconds (default: 1 hour = 3600000).

💻 Usage Examples

Analyzing Dependencies

Analyze dependencies in a codebase and generate a dependency graph.

const result = await client.callTool("DependencyMCP", "analyze_dependencies", {
  path: "/path/to/project",
  excludePatterns: ["node_modules", "dist"], // Optional parameter
  maxDepth: 10, // Optional parameter
  fileTypes: [".ts", ".js", ".cs"] // Optional parameter
});

Getting the Dependency Graph

Get the dependency graph of a codebase in JSON or DOT format.

const result = await client.callTool("DependencyMCP", "get_dependency_graph", {
  path: "/path/to/project",
  format: "dot" // Or "json" (default)
});

Getting File Metadata

Get detailed information about a specific file.

const result = await client.callTool("DependencyMCP", "get_file_metadata", {
  path: "/path/to/file.ts"
});

Architectural Scoring

Evaluate the codebase's compliance with architectural rules and patterns.

const result = await client.callTool("DependencyMCP", "architecture_score", {
  path: "/path/to/project"
});

Output Examples

Dependency Graph (JSON Format):

{
  "nodes": [
    { "id": "1", "label": "main" },
    { "id": "2", "label": "dependencies" }
  ],
  "edges": [
    { "from": "1", "to": "2", "label": "depends-on" }
  ]
}

Architectural Score (JSON Format):

{
  "score": 85,
  "description": "The codebase complies with 85% of the architectural rules."
}

🔧 Technical Details

Technology Stack

• TypeScript
• Zod: For type-safe configuration.
• Diff: For file difference comparison.
• Minimatch: For file pattern matching.

Project Structure

dependency-mcp/
├── src/
│   ├── index.ts        # Entry file
│   ├── graph.ts       # Graph generation logic
│   └── architecture.ts # Architectural analysis module
└── package.json      # Dependency management file

Adding a New Language

1. Update the fileTypes list to include the file extensions of the new language.
2. Implement support for the new language to ensure correct parsing and processing.

📄 License

This project is licensed under the MIT License.