This project provides an MCP (Meta-Context Protocol) server, acemcp, designed to enable efficient code indexing and semantic search for AI context engines like ACE. It targets developers and researchers who need to quickly find relevant code snippets within large codebases using natural language queries. The primary benefit is streamlined code context retrieval with automatic indexing and robust file handling.

How It Works

Acemcp functions as a server that indexes code repositories and exposes a search_context tool. Its core approach involves automatic incremental indexing, where only new or modified files are processed before each search query, ensuring results are always up-to-date without manual intervention. It employs semantic search, allowing users to query codebases using natural language descriptions. The system automatically handles multiple file encodings (UTF-8, GBK, GB2312, Latin-1) and respects .gitignore patterns, making it adaptable to diverse project structures and internationalized codebases.

Quick Start & Requirements

• Installation: Recommended: uv tool install acemcp. Temporary run: uvx acemcp. Development: Clone the repository, cd acemcp, uv sync, then uv run acemcp.
• Prerequisites: uv package manager. No specific hardware (e.g., GPU) or advanced software dependencies like CUDA are mentioned.
• Configuration: Settings like BATCH_SIZE, MAX_LINES_PER_BLOB, BASE_URL, TOKEN, TEXT_EXTENSIONS, and EXCLUDE_PATTERNS are configured via ~/.acemcp/settings.toml, command-line arguments, environment variables, or a web management interface.
• MCP Integration: Requires adding a JSON configuration to MCP clients.
• Web Management Interface: Accessible via --web-port argument (e.g., http://localhost:8888), offering configuration management and real-time logs.

Highlighted Details

• Automatic Incremental Indexing: Indexes only changed files before each search, optimizing performance and ensuring data freshness.
• Semantic Code Search: Utilizes natural language queries for context retrieval, offering more relevant results than simple keyword matching.
• Multi-Encoding Support: Automatically detects and processes files encoded in UTF-8, GBK, GB2312, and Latin-1, with a fallback to UTF-8.
• .gitignore Integration: Seamlessly adheres to exclusion patterns defined in the project's .gitignore file.
• Web Management Interface: Provides real-time server status, logs via WebSocket with intelligent reconnection, and tool debugging capabilities.

Maintenance & Community

The provided README does not detail specific contributors, sponsorships, or community channels (like Discord or Slack). The latest version mentioned is 0.1.3.

Licensing & Compatibility

The license type is not specified in the provided README content. This information is crucial for assessing commercial use or closed-source linking compatibility.

Limitations & Caveats

The project is at version 0.1.3, suggesting it may still be in early development. Crucially, the license is not stated, which is a significant adoption blocker. No specific performance benchmarks or known bugs are detailed.