Content
# Octocode MCP - Smart Assistant for Code Context Creation
**The missing piece for AI agents that need quality code context. Transform any AI assistant into a code research expert that enriches context for better code handling, documentation, and complex ecosystem solutions.**
<div align="center">
<img src="https://github.com/bgauryy/octocode-mcp/raw/main/packages/octocode-mcp/assets/logo_white.png" width="400px" alt="Octocode Logo">
</div>
<div align="center">
[](./package.json)
[](./package.json)
[](https://nodejs.org/)
[](https://github.com/modelcontextprotocol/servers)
[](https://deepwiki.com/bgauryy/octocode-mcp)
[](https://archestra.ai/mcp-catalog/bgauryy__octocode-mcp)
</div>
## 🎯 Why Octocode MCP?
Octocode MCP closes the code‑context gap by giving AI assistants secure, real-time access to public/private code anywhere so they reason from real implementations and have a better, more quality context.
### 🚀 Core capabilities
- 🌍 context generation from code anywhere
- 🔍 Smart semantic code discovery
- 🌟 Learn and search anything from top public repositories
- 🧭 Discover anything from complex multi‑repo scenarios
- 🏗️ Ecosystem‑aware solutions across stacks and orgs
- 📚 Docs and example enrichment from production code
- 🔄 Progressive research flows for deep understanding
### 💡 Ideal for
- Code creation, complex bug fixes, architecture insight, documentation, learning, and navigating large codebases...
## 🚀 Quick Setup
### Prerequisites
- **Node.js** >= 18.12.0
- **GitHub Authentication** (choose one method below)
### Authentication Setup
**Option 1: [GitHub CLI](https://cli.github.com/) (Recommended)**
```bash
# Install GitHub CLI if needed
# macOS: brew install gh
# Windows: winget install --id GitHub.cli
# Authenticate
gh auth login
```
**Option 2: Personal Access Token**
1. Create token at [GitHub Settings → Personal Access Tokens](https://github.com/settings/tokens)
2. Required scopes: `repo`, `read:user`, `read:org`
### MCP Configuration
Add to your AI assistant's MCP configuration:
**With GitHub CLI:**
```json
{
"mcpServers": {
"octocode": {
"command": "npx",
"args": ["octocode-mcp@latest"]
}
}
}
```
**With Personal Access Token:**
```json
{
"mcpServers": {
"octocode": {
"command": "npx",
"args": ["octocode-mcp@latest"],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
}
}
}
}
```
**That's it!** Your AI assistant can now search and analyze GitHub repositories.
## 🛠️ Available Research Tools
| Tool | Purpose | Default | Description |
|------|---------|---------|-------------|
| **`githubSearchCode`** | Code Discovery | ✅ | Search code across repositories with semantic queries |
| **`githubSearchRepositories`** | Repository Discovery | ✅ | Find repositories by topic, language, or description |
| **`githubViewRepoStructure`** | Structure Analysis | ✅ | Explore repository file structure and navigation |
| **`githubGetFileContent`** | Content Access | ✅ | Fetch specific files or code sections with context |
| **`githubSearchPullRequests`** | History Analysis | ❌ | Analyze pull requests and code changes |
**Default tools** are automatically enabled. **Non-default tools** require configuration (see Advanced Setup below).
## 🎯 Real-World Context Creation Examples
**Code Creation Context:**
```
"I need to implement OAuth2 in my Node.js app - show me real implementations"
→ Finds proven OAuth2 patterns → Analyzes security practices → Provides implementation context
```
**Complex Ecosystem Solutions:**
```
"How do large organizations handle microservices communication?"
→ Discovers enterprise patterns → Examines real architectures → Explains design decisions
```
**Documentation Enhancement:**
```
"Find real examples of GraphQL error handling for my API docs"
→ Searches GraphQL implementations → Extracts error patterns → Provides documentation examples
```
**Best Practices Discovery:**
```
"What are the current best practices for React state management in 2024?"
→ Analyzes modern React apps → Compares state solutions → Identifies trending patterns
```
**See the dramatic difference in AI assistant capability:**
**[🎯 Live Demo: ThreeJS Code Creation Comparison](https://octocode-sonnet4-gpt5-comparisson.vercel.app/)**
This interactive comparison shows how Octocode MCP transforms AI assistants from providing generic code suggestions to delivering expert-level, context-rich implementations with real-world patterns and best practices.
## 📺 Examples
### Example 1: Deep code research with Octocode
- **Prompt**:
```
Explain deeply how React hooks work under the hood, using information from code and documents.
Provide a technical explanation, covering both basic and advanced concepts.
Do a deep research
```
- **Video**: [YouTube](https://www.youtube.com/watch?v=BCOpsRjAPU4&t=9s)
### Example 2: Learn about AI Agents using Octocode
- **Goal**: Create context for agents creation
- **Video**: [YouTube](https://www.youtube.com/watch?v=rhQ3nTwU9kw)
### Example 3: Review PRs using Octocode
- **Video**: [YouTube](https://www.youtube.com/watch?v=rhQ3nTwU9kw)
## ⚙️ Advanced Configuration
### Tool Selection
```bash
# Run only specific tools (exclusive mode)
export TOOLS_TO_RUN="githubSearchCode,githubSearchRepositories"
# Enable additional tools (additive mode)
export ENABLE_TOOLS="githubSearchPullRequests"
# Disable specific default tools
export DISABLE_TOOLS="githubViewRepoStructure"
# Enable experimental features
export BETA="1"
```
**Note:** `TOOLS_TO_RUN` cannot be combined with `ENABLE_TOOLS`/`DISABLE_TOOLS`.
### Enterprise Features
- **Content Sanitization**: Automatic detection and redaction of sensitive data
- **Smart Token Management**: Efficient content reduction for large codebases
- **Access Control**: Uses your GitHub permissions (public/private repositories)
- **Rate Limiting**: Built-in GitHub API rate limit handling
## 📚 Documentation & Resources
| Resource | Description |
|----------|-------------|
| **[🌐 octocode.ai](https://octocode.ai)** | Official website |
| **[📺 YouTube Channel](https://www.youtube.com/@Octocode-ai)** | Video tutorials and demos |
| **[📚 Usage Guide](./packages/octocode-mcp/docs/USAGE_GUIDE.md)** | 20+ examples and best practices |
| **[🔐 Authentication Guide](./packages/octocode-mcp/docs/AUTHENTICATION.md)** | Complete setup and enterprise features |
| **[🔧 Tool Schemas](./packages/octocode-mcp/docs/TOOL_SCHEMAS.md)** | Complete API reference for all tools |
| **[🏗️ Architecture Overview](./packages/octocode-mcp/docs/summary.md)** | System design and performance details |
| **[🧰 octocode-utils](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-utils)** | Utility library for token-efficient minification and helpers used by Octocode |
### 🤖 Claude Plugin & Agent System
**[Octocode Claude Plugin](./octocode-claude-plugin/)** - Multi-agent system for Claude AI with specialized agents for product, architecture, UX, implementation, and verification workflows.
**Key Features:**
- Multi-agent workflow orchestration for complex development tasks
- Specialized agents (Product, Architect, UX, Implementation, Verification)
- Integration with Octocode MCP for enhanced code context
- Session management and progress tracking
- Comprehensive testing and verification workflows
### 📚 Code Generation Resources
**[Octocode Resources](./resources/)** - Curated collection of 610+ GitHub repositories for building production-ready Node.js/TypeScript applications with 2025 best practices.
**What's Included:**
- **[project-examples.md](./resources/project-examples.md)** - T3 Stack, production boilerplates, monorepo patterns
- **[frontend.md](./resources/frontend.md)** - React 19, Next.js 15, state management, UI libraries, React Native
- **[backend.md](./resources/backend.md)** - NestJS, Fastify, tRPC, API design patterns
- **[oauth.md](./resources/oauth.md)** - Authentication, OAuth 2.0/2.1, NextAuth.js, security patterns
- **[architecture.md](./resources/architecture.md)** - System design, Clean Architecture, DDD, microservices
- **[database.md](./resources/database.md)** - Prisma, TypeORM, database design, ORMs comparison
- **[frameworks.md](./resources/frameworks.md)** - Next.js features, UI libraries, charts, 3D graphics
- **[testing.md](./resources/testing.md)** - Vitest, Playwright, testing strategies
- **[security.md](./resources/security.md)** - OWASP Top 10 2025, secrets management, zero-trust
- **[infrastructure.md](./resources/infrastructure.md)** - Docker, Kubernetes, CI/CD, monitoring
- **[ai-agents.md](./resources/ai-agents.md)** - AI frameworks, RAG, vector databases, LangChain
- **[mcp-typescript.md](./resources/mcp-typescript.md)** - Model Context Protocol, AI SDK, TypeScript AI tools
- **[tooling.md](./resources/tooling.md)** - Development tools, linters, monorepo tooling
- **[learning.md](./resources/learning.md)** - Career roadmaps, interview prep, learning paths
**Purpose:** Context resources for AI agents using Octocode MCP to generate applications with proven patterns and best practices from the Node.js/TypeScript ecosystem.
## 🌟 Featured On
### Official Community MCP Server
[](https://github.com/modelcontextprotocol/servers) **modelcontextprotocol/servers**
### Community Collections
- [](https://github.com/punkpeye/awesome-mcp-servers) **punkpeye/awesome-mcp-servers**
- [](https://github.com/appcypher/awesome-mcp-servers) **appcypher/awesome-mcp-servers**
- [](https://github.com/wong2/awesome-mcp-servers) **wong2/awesome-mcp-servers**
- [](https://github.com/Puliczek/awesome-mcp-security) **Puliczek/awesome-mcp-security**
### MCP Directories & Tools
- [](https://glama.ai/mcp/servers/@bgauryy/octocode-mcp)
- [](https://mcp.so/server/octocode/bgauryy)
- [](https://www.pulsemcp.com/servers/bgauryy-octocode)
- [](https://devtool.io/tool/octocode-mcp)
- [](https://www.mcpserverfinder.com/servers/bgauryy/octocode-mcp)
- [](https://mcp-container.com/en/mcp/137e872e-ef4f-4bdb-a697-d1e628200215)
## 💬 Support & Community
- **Issues & Bugs:** [GitHub Issues](https://github.com/bgauryy/octocode-mcp/issues)
- **Discussions:** [GitHub Discussions](https://github.com/bgauryy/octocode-mcp/discussions)
- **Documentation:** [octocode.ai](https://octocode.ai)
---
<a href="https://glama.ai/mcp/servers/@bgauryy/octocode-mcp">
<img width="380" height="200" src="https://glama.ai/mcp/servers/@bgauryy/octocode-mcp/badge" />
</a>
<div align="center">
<p>Built with ❤️ for developers</p>
<p>
<a href="https://octocode.ai">Website</a> •
<a href="https://github.com/bgauryy/octocode-mcp">GitHub</a> •
<a href="https://www.npmjs.com/package/octocode-mcp">NPM</a> •
<a href="https://discord.gg/octocode">Discord</a>
</p>
</div>
Connection Info
You Might Also Like
mcp-chrome
MCP Server transforms Chrome into an AI-powered automation tool.
firecrawl
Firecrawl MCP Server enables web scraping, crawling, and content extraction.
Firecrawl
Firecrawl MCP Server enables web scraping, crawling, and content extraction.
RAGLight
RAGLight is a modular Python library for Retrieval-Augmented Generation,...
Semgrep
The Semgrep MCP server is now part of the main Semgrep repository.
mcp-mem0
MCP-Mem0 is a template for building MCP servers with persistent memory for AI agents.