This project provides a high-performance Model Context Protocol (MCP) server for AI assistants, enabling efficient code repository indexing and semantic search. It allows AI tools to quickly understand large codebases, retrieve precise code snippets with line numbers, and benefit from automatic incremental indexing, enhancing AI-assisted code analysis and developer productivity.

How It Works

The server implements the MCP protocol, focusing on efficient code indexing and semantic search. Its core approach features incremental indexing, processing only new or modified files. Key optimizations include intelligent file splitting, batch uploads, and SHA-256 caching. The system respects .gitignore rules, supports multiple character encodings (UTF-8, GBK, etc.), and provides AI-friendly output with file paths and line numbers. Robust WSL path handling is also a core feature.

Quick Start & Requirements

Installation is recommended via NPM: npm install -g acemcp-node (global) or npm install acemcp-node (local). Requirements include Node.js >= 18.0.0, npm >= 8.0.0, and compatible OS (Windows 10+, Linux, macOS, WSL 2). Configuration is managed via settings.toml and command-line arguments.

Highlighted Details

• Performance: Features incremental indexing, batch uploads, intelligent file splitting, and SHA-256 caching for efficient processing.
• Developer Experience: Built with TypeScript, includes a web management interface for real-time logs, configuration editing, and tool debugging, and respects .gitignore patterns.
• Compatibility: Strong cross-platform support (Windows, Linux, macOS, WSL) with advanced path handling. Supports multiple character encodings and shares configuration/data with the Python version.
• Web Management Interface: Provides a local web UI (defaulting to port 8080) for monitoring server status, managing configurations, viewing live logs, and testing MCP tools.

Maintenance & Community

Maintained by yeuxuan on GitHub. No specific community channels (like Discord/Slack) or notable partnerships are detailed in the README.

Licensing & Compatibility

Ace-Mcp-Node is released under the permissive ISC License, making it suitable for commercial use and integration into closed-source projects. It is designed to be fully compatible with the Acemcp-Python version, allowing seamless switching and shared data.

Limitations & Caveats

The web interface is intentionally bound to localhost for security, requiring SSH tunneling or reverse proxy configurations for remote access. Users encountering specific environment-related path or encoding issues may need to consult the detailed troubleshooting guides provided.