NyxDocs
MCP server for real-time cryptocurrency project documentation and insights.
Key Features
Use Cases
README
NyxDocs - Cryptocurrency Documentation MCP Server
NyxDocs is a specialized Model Context Protocol (MCP) server that provides comprehensive documentation management for cryptocurrency projects. Built with Python and inspired by Context7's architecture, it offers real-time access to crypto project documentation, blockchain information, and development resources.
🚀 Features
Core Capabilities
- Multi-Blockchain Support: Ethereum, BSC, Polygon, Solana, and more
- Real-time Documentation: Automatically discovers and updates project docs
- Smart Search: Find projects by name, category, or blockchain
- Content Extraction: Supports GitHub, GitBook, Notion, and official websites
- Update Monitoring: Tracks documentation changes automatically
MCP Tools
search_crypto_projects: Search cryptocurrency projects by various criteriaget_project_info: Detailed project information with blockchain contextget_documentation: Retrieve actual documentation contentlist_blockchains: Available blockchain networkscheck_updates: Recent documentation updates
🏗️ Architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Data Sources │ │ NyxDocs Core │ │ MCP Client │
│ │ │ │ │ │
│ • CoinGecko API │────│ • Project DB │────│ • Claude │
│ • GitHub API │ │ • Doc Scraper │ │ • Cursor │
│ • GitBook │ │ • Update Monitor │ │ • VS Code │
│ • Notion │ │ • MCP Server │ │ • Other Clients │
└─────────────────┘ └──────────────────┘ └─────────────────┘
Key Components
- MCP Server Core: FastMCP-based server handling protocol communication
- Data Collectors: Modules for gathering project information from various APIs
- Documentation Scrapers: Intelligent content extraction from different sources
- Database Layer: SQLite/PostgreSQL for storing projects and documentation
- Update Monitors: Background tasks for tracking documentation changes
📦 Installation
Prerequisites
- Python 3.11+
- uv (recommended) or pip
Quick Start
# Clone the repository
git clone https://github.com/nyxn-ai/NyxDocs.git
cd NyxDocs
# Install with uv (recommended)
uv sync
# Or install with pip
pip install -e .
# Set up environment
cp .env.example .env
# Edit .env with your API keys
# Initialize database
uv run python -m nyxdocs.database.init
# Start the server
uv run python -m nyxdocs.server
MCP Client Configuration
Cursor
{
"mcpServers": {
"nyxdocs": {
"command": "uv",
"args": ["run", "python", "-m", "nyxdocs.server"]
}
}
}
Claude Desktop
{
"mcpServers": {
"nyxdocs": {
"command": "uv",
"args": ["run", "python", "-m", "nyxdocs.server"]
}
}
}
🔧 Configuration
Environment Variables
# API Keys
COINGECKO_API_KEY=your_coingecko_api_key
GITHUB_TOKEN=your_github_token
# Database
DATABASE_URL=sqlite:///nyxdocs.db
# Or for PostgreSQL: postgresql://user:pass@localhost/nyxdocs
# Server Settings
LOG_LEVEL=INFO
UPDATE_INTERVAL=3600 # seconds
MAX_CONCURRENT_SCRAPES=5
Supported Data Sources
- CoinGecko: Market data and project information
- GitHub: Repository documentation and README files
- GitBook: Hosted documentation platforms
- Notion: Project documentation pages
- Official Websites: Direct documentation scraping
🛠️ Usage Examples
Search for DeFi Projects
# In your MCP client
search_crypto_projects(query="uniswap", category="DeFi", blockchain="ethereum")
Get Project Documentation
get_documentation(project="uniswap", format="markdown")
Monitor Updates
check_updates(since="2024-01-01", limit=10)
🧪 Development
Project Structure
NyxDocs/
├── nyxdocs/
│ ├── __init__.py
│ ├── server.py # Main MCP server
│ ├── collectors/ # Data collection modules
│ ├── scrapers/ # Documentation scrapers
│ ├── database/ # Database models and operations
│ ├── tools/ # MCP tool implementations
│ └── utils/ # Utility functions
├── tests/ # Test suite
├── docs/ # Documentation
├── pyproject.toml # Project configuration
└── README.md
Running Tests
uv run pytest
Code Quality
uv run ruff check
uv run mypy nyxdocs
📚 Documentation
🤝 Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Inspired by Context7 by Upstash
- Built with Python MCP SDK
- Cryptocurrency data provided by CoinGecko API
NyxDocs - Making cryptocurrency project documentation accessible and up-to-date for AI assistants.
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
Web3 MCP
A Model Context Protocol server for unified blockchain data access.
Web3 MCP is a Model Context Protocol server that provides access to blockchain data through Ankr's Advanced API. It allows large language models to interact seamlessly with multiple blockchain networks such as Ethereum, BSC, Polygon, and Avalanche. With support for NFT, token, and blockchain query APIs, it enables users and AI agents to retrieve on-chain data, statistics, and analytics efficiently within an MCP context.
- ⭐ 3
- MCP
- tumf/web3-mcp
GXtract MCP Server
MCP server for seamless GroundX platform integration with modern editors.
GXtract MCP Server implements the Model Context Protocol (MCP) to facilitate direct integration between the GroundX document understanding platform and editors such as VS Code. It offers tools for document search, querying, and semantic object explanations, leveraging Python 3.12+ and FastMCP v2 for high performance. The system includes an in-memory cache to boost efficiency and reduce API calls, with support for both stdio and HTTP transport layers for maximum flexibility.
- ⭐ 1
- MCP
- sascharo/gxtract
FastMCP
The fast, Pythonic way to build MCP servers and clients.
FastMCP is a production-ready framework for building Model Context Protocol (MCP) applications in Python. It streamlines the creation of MCP servers and clients, providing advanced features such as enterprise authentication, composable tools, OpenAPI/FastAPI generation, server proxying, deployment tools, and comprehensive client libraries. Designed for ease of use, it offers both standard protocol support and robust utilities for production deployments.
- ⭐ 20,201
- MCP
- jlowin/fastmcp
Code Declaration Lookup MCP Server
Fast, language-agnostic code declaration search and lookup server via MCP.
Provides a Model Context Protocol (MCP) server that indexes code declarations using universal ctags and SQLite with FTS5 full-text search. Offers search and listing functionality for functions, classes, structures, enums, and other code elements across any language supported by ctags. Enables seamless integration with coding agents for dynamic indexing, respects .gitignore, and supports ctags file ingestion and management.
- ⭐ 2
- MCP
- osinmv/function-lookup-mcp
Yuque-MCP-Server
Seamless integration of Yuque knowledge base with Model-Context-Protocol for AI model context management.
Yuque-MCP-Server provides an MCP-compatible server for interacting with the Yuque knowledge base platform. It enables AI models to retrieve, manage, and analyze Yuque documents and user information through a standardized Model-Context-Protocol interface. The server supports operations such as document creation, reading, updating, deletion, advanced search, and team statistics retrieval, making it ideal for AI-powered workflows. Inspired by Figma-Context-MCP, it facilitates contextual awareness and dynamic knowledge management for AI applications.
- ⭐ 31
- MCP
- HenryHaoson/Yuque-MCP-Server
ZoomEye MCP Server
Real-time cyberspace asset intelligence for AI assistants via Model Context Protocol.
ZoomEye MCP Server implements the Model Context Protocol (MCP) to provide network asset intelligence to AI assistants and development tools. It enables querying of global internet assets through ZoomEye's cyber asset search engine using structured parameters and dorks. The server includes features like caching, error handling, and compatibility with leading MCP environments, supporting real-time cyber asset data integration for various AI and developer platforms.
- ⭐ 50
- MCP
- zoomeye-ai/mcp_zoomeye
Didn't find tool you were looking for?