- First NetworkX integration for Model Context Protocol
- Enables graph analysis and visualization in AI conversations
- Supports 13 operations including centrality, PageRank, community detection
- Production-ready v1.0.0 available on PyPI
Added 8b-is/smart-tree to all language README files including the main English README.md
with appropriate translations. Smart Tree is an AI-native directory visualization tool
with semantic analysis, ultra-compressed formats for AI consumption, and 10x token reduction.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
What is Octocode? 🐙
The perfect code assistant that can help understand anything. Octocode was built to understand connections between Github repositories and NPM packages under any privilege level you have. With AI-powered advanced search, heuristic discovery, and smart fallbacks, it makes GitHub's vast repository of knowledge truly searchable and analyzable.
It already integrated into
https://github.com/modelcontextprotocol/servers
You can visit here to learn more:
http://octocode.ai/
Server Details
This server knows to do smart code research and using users privileges (npm & github) to fetch and analysis code and docs in real time!
Motivation and Context
It started as a personal tool while working at Wix to solve the challenge of navigating large private/public codebases and keeping up with rapidly evolving technology.
Evolved from a side project into a comprehensive code assistant which in use in many teams and solves many problems that we needed to understand in a long time (e.g. legacy projects and complex dependencies trees). It also lets understand public code (I used this MCP to understand modelcontextprotocol better during development..)
Core Purpose:
Make code exploration as intelligent as having a senior developer guide you through any codebase
Help developers understand "how does this work?" rather than just managing projects
Key Problems it Solves:
Code Understanding: Makes GitHub's vast repository of knowledge truly searchable and analyzable
Connection Discovery: Built to understand connections between repositories and NPM packages across any privilege level
Smart Search: Provides AI-powered advanced search with heuristic discovery and smart fallbacks
Unique Approach:
Uses AI-powered search to find relevant code even with vague queries
Maps relationships between NPM packages, repositories, and dependencies
Works across public, private, and organization repositories
Requires zero configuration and no personal access tokens (works using gh and npm CLI)
The tool essentially aims to be "the perfect code assistant that can help understand anything" by making complex codebases and technical implementations more accessible and understandable through intelligent search and discovery.
How Has This Been Tested?
I'm using it personally and many developers (mostly in WIx) are using it to solve day-to-day challenges. As a senior developer I leverage this tool to help others and let them find solutions themselves.
This MCP is heavily tested.
Additional context
The installation is super easy.
prerequisites:
npm cli installed
gh cli installed (brew install gh, gh auth login)
and then just configure the MCP:
"octocdode-mcp": {
"command": "npx",
"args": [
"octocode-mcp"
]
},
How Octocode is different than Gitbhub Official MCP
ctocode MCP is superior to GitHub's official MCP in the manner of code research in several key ways:
More Developer-Friendly: Built by developers for developers, focusing on real-world code exploration needs
Smarter Search: More sophisticated search algorithms with better understanding of developer intent
Ecosystem Integration: Unique integration of GitHub and NPM ecosystems provides a more complete development picture
Better Results: More relevant and contextual results with intelligent analysis and filtering
Performance: Smart caching and query optimization for faster responses
While GitHub's MCP provides solid basic functionality, Octocode is clearly designed for more sophisticated code exploration and understanding, making it the better choice for developers who need deep code insight and efficient navigation across almost any ecosystem.
