#artificial-intelligence #mcp #context-protocol

nightly oak-mcp

Oak MCP server with support for compact code structures and fuzzy semantic search

6 releases

Uses new Rust 2024

new 0.0.6 Mar 4, 2026
0.0.5 Mar 3, 2026
0.0.4 Feb 15, 2026
0.0.2 Jan 30, 2026

#537 in Development tools

Download history 109/week @ 2026-01-27 98/week @ 2026-02-03 275/week @ 2026-02-10 148/week @ 2026-02-17 195/week @ 2026-02-24

745 downloads per month
Used in 122 crates (121 directly)

MPL-2.0 license

410KB
6K SLoC

🚀 oak-mcp

Crates.io Documentation

Model Context Protocol Integration for Oak — Enable AI assistants to understand and analyze code through the MCP standard.

🎯 Why oak-mcp?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to interact with development tools and codebases. oak-mcp bridges Oak's parsing capabilities with MCP, allowing AI agents to perform code analysis and understanding tasks.

✨ Key Features

  • 🤖 MCP Server Implementation — Standard MCP server exposing Oak's language analysis
  • 📊 Code Analysis Tools — Parsing, symbol extraction, and navigation as MCP tools
  • 🔍 Semantic Understanding — Query symbol definitions, references, and documentation
  • 📁 Project-Wide Analysis — Multi-file project understanding via oak-vfs
  • 🌐 Language Agnostic — Works with any Oak language parser

🏗️ Architecture

MCP Tools Provided

Tool Description
parse_file Parse source file and return AST structure
find_symbols Search for symbols matching a query
get_definition Get definition location of a symbol
find_references Find all references to a symbol
get_hover Get hover information for a position

🔗 Ecosystem Integration

Integrates with oak-core for parsing, oak-vfs for file access, oak-navigation for code navigation, and any MCP-compatible AI assistant.

📖 Documentation

For usage examples and API details, see the API documentation.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Dependencies

~14–20MB
~264K SLoC