MCP Code Indexer

🚀 MCP Code Indexer

An intelligent code retrieval tool based on the Model Context Protocol (MCP), providing efficient and accurate code library retrieval capabilities for large AI language models.

English Version

🚀 Quick Start

The MCP Code Indexer is a code retrieval tool designed specifically for large AI language models. Through vectorized indexing and semantic understanding, it helps AI better understand and analyze code libraries, significantly improving the efficiency and accuracy of code-related tasks.

Project Address: https://github.com/zxfgds/mcp-code-indexer

✨ Features

Intelligent Code Retrieval

• Semantic-based code search: Understands the meaning of code rather than just keyword matching.
• Cross-language code retrieval: Supports code search across different programming languages.
• Intelligent code snippet extraction: Automatically identifies the complete code context.

Code Analysis Capabilities

• Code structure analysis: Analyzes classes, functions, and dependency relationships.
• Code quality assessment: Evaluates the quality of code.
• Documentation and comment extraction: Extracts documentation and comments from code.
• Similar code detection: Detects similar code snippets.
• Code metric statistics: Calculates code metrics.
• Project dependency analysis: Analyzes project dependencies.

Optimized Context Processing

• Intelligent Token consumption control: Reduces unnecessary context information.
• Structured code context provision: Provides structured code context.
• Multi-project parallel indexing and retrieval: Supports parallel indexing and retrieval of multiple projects.
• Persistent project identification: Avoids repeated indexing.

Full MCP Protocol Support

• Compliance with MCP data interaction specifications: Meets the MCP data interaction standards.
• Rich toolset provision: Provides a rich set of tools.
• Asynchronous operation and progress feedback: Supports asynchronous operations and provides progress feedback.

📚 Documentation

Application Scenarios

Claude Desktop Application

• Enhanced code understanding: Helps Claude understand the user's code library more accurately and provide more precise suggestions and answers.
• Intelligent code navigation: Quickly locates relevant code snippets and improves the efficiency of Q&A.
• Code quality improvement: Provides more professional code optimization suggestions through code analysis functions.
• Project dependency management: Helps understand and manage project dependencies.
• Documentation generation assistance: Assists in generating technical documentation based on code comments and structure analysis.

VSCode Extension

• Real-time code analysis: Obtains code analysis results directly in the editor.
• Intelligent code recommendation: Provides more accurate code suggestions based on project context.
• Refactoring assistance: Identifies code patterns that can be optimized and assists in code refactoring.
• Dependency relationship visualization: Intuitively displays code dependencies.
• Team collaboration enhancement: Helps team members better understand the code library.

📦 Installation

Install Dependencies

pip install -r requirements.txt

Install the Tool

python setup.py install

Configuration Instructions

Claude Desktop Configuration

• Open Claude Desktop and go to the plugin marketplace to install the MCP Code Indexer.
• Select "MCP Code Indexer" in the plugin settings and complete the configuration as prompted.

VSCode Configuration

1. Open Visual Studio Code.
2. Go to the Extensions marketplace, search for "MCP Code Indexer" and install it.
3. After installation, find the MCP-related options in the Settings and configure them.

💻 Usage Examples

Basic Usage

Right-click on a selected code snippet in the code editor and select "MCP Code Indexer" for retrieval or analysis.

Advanced Usage

Enter mcp-indexer:<command> in the command palette to perform specific tasks, such as indexing projects and analyzing dependencies.

Project Value

1. Improve efficiency: Reduce repetitive work and increase development speed.
2. Optimize resources: Make reasonable use of computing resources and reduce Token consumption.
3. Enhance collaboration: Promote team code review and knowledge sharing.
4. Ensure quality: Ensure code maintainability and reliability through automated analysis.

Contribution Guidelines

We welcome contributions to the project. Please submit issues, suggestions, or pull requests through Issues.

📄 License

This project is licensed under the MIT License.