Enterprise Documentation Server

🚀 Overview

Enterprise MCP Documentation Server is a powerful, self-hosted Model Context Protocol (MCP) server that provides up-to-date documentation for enterprise and development tools directly to AI coding assistants like Claude Code, Cursor, and Windsurf.

Unlike traditional approaches that rely on stale training data, this server fetches and processes live documentation from official sources, ensuring your AI assistant always has accurate, current information.

Why This Project?

🔍 No More Hallucinations: Stop getting outdated API examples
🏢 Enterprise Ready: Supports internal tools like Proxmox, Nessus, TopDesk
🔒 Privacy First: Self-hosted, no data leaves your infrastructure
⚡ Smart Caching: Redis-backed performance optimization
🧩 Modular Design: Easy to extend with new tools
🎯 Context7 Compatible: Integrates with existing solutions

🛠️ Supported Tools

Category	Tools	Status
Search & Analytics	Elasticsearch	✅ Complete
Containerization	Docker, Docker Compose	✅ Complete
Programming	Python 3.x Documentation	✅ Complete
Automation	n8n Workflows	✅ Complete
AI/ML	Ollama	✅ Complete
Virtualization	Proxmox VE	✅ Complete
Security	Nessus Professional	✅ Complete
Service Management	TopDesk	✅ Complete
Collaboration	Confluence	✅ Complete
Version Control	Git, GitHub	🚧 Planned
Infrastructure	Terraform, Ansible	🚧 Planned

📋 Requirements

• Python 3.9+
• Redis (for caching)
• 4GB+ RAM (for embeddings)
• Internet access (for documentation crawling)

🔧 Installation

Option 1: pip install (Recommended)

pip install enterprise-mcp-docs

Option 2: Docker

# Using docker-compose (includes Redis)
git clone https://github.com/hasecon/enterprise-mcp-docs.git
cd enterprise-mcp-docs
docker-compose up -d

Option 3: From Source

git clone https://github.com/hasecon/enterprise-mcp-docs.git
cd enterprise-mcp-docs
pip install -e .

⚙️ Configuration

1. Basic Setup

# Copy configuration template
cp config/default.json config/local.json

# Set environment variables
cp .env.example .env

2. Configure Tools

Edit config/local.json:

{
  "tools": {
    "elasticsearch": {
      "provider": "Elasticsearch",
      "base_url": "https://www.elastic.co/guide/en/elasticsearch/reference/current/",
      "sections": ["getting-started", "search", "mapping", "query-dsl"],
      "cache_ttl": 3600,
      "enabled": true
    },
    "docker": {
      "provider": "Docker", 
      "base_url": "https://docs.docker.com/",
      "sections": ["get-started", "build", "compose"],
      "cache_ttl": 7200,
      "enabled": true
    }
  },
  "vector_db": {
    "enabled": true,
    "embedding_model": "all-MiniLM-L6-v2"
  },
  "cache": {
    "redis_url": "redis://localhost:6379",
    "ttl": 3600
  }
}

3. Initialize Documentation

# Crawl all enabled tools
enterprise-mcp-docs crawl --all

# Or crawl specific tools
enterprise-mcp-docs crawl --tool elasticsearch
enterprise-mcp-docs crawl --tool docker

🚦 Usage

Start the MCP Server

# Start server
enterprise-mcp-docs serve

# Or with custom config
enterprise-mcp-docs serve --config config/production.json

Claude Code Integration

Add to your Claude Code configuration:

{
  "mcpServers": {
    "enterprise-docs": {
      "command": "python",
      "args": ["-m", "enterprise_mcp_docs.server"],
      "env": {}
    }
  }
}

Cursor Integration

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "enterprise-docs": {
      "command": "enterprise-mcp-docs",
      "args": ["serve"]
    }
  }
}

Example Queries

Once configured, you can ask Claude Code:

How do I create an Elasticsearch mapping for user data?
Show me Docker Compose syntax for a web application with Redis.
What are the best practices for n8n workflow error handling?
How do I configure Proxmox clustering with shared storage?

🔌 Adding New Providers

1. Create Provider Class

# src/enterprise_mcp_docs/providers/mytool.py
from .base import BaseProvider

class MyToolProvider(BaseProvider):
    async def crawl_docs(self):
        # Implement crawling logic
        docs = []
        # ... fetch and process docs
        await self.add_to_vector_db(docs)
        return docs

2. Add Configuration

{
  "tools": {
    "mytool": {
      "provider": "MyTool",
      "base_url": "https://mytool.com/docs/",
      "sections": ["api", "guides"],
      "cache_ttl": 3600,
      "enabled": true
    }
  }
}

3. Test and Submit PR!

🧪 Development

Setup Development Environment

git clone https://github.com/hasecon/enterprise-mcp-docs.git
cd enterprise-mcp-docs

# Install development dependencies
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

Running Tests

# Run all tests
pytest

# Run with coverage
pytest --cov=enterprise_mcp_docs

# Run specific test types
pytest -m unit
pytest -m integration

Code Quality

# Format code
black src/ tests/
isort src/ tests/

# Type checking
mypy src/

# Linting
flake8 src/ tests/

🐳 Docker Deployment

Development

docker-compose -f docker-compose.dev.yml up

Production

docker-compose -f docker-compose.prod.yml up -d

📊 Monitoring

The server exposes metrics on /metrics endpoint:

• Documentation fetch success/failure rates
• Cache hit ratios
• Search query performance
• Vector similarity scores

🤝 Contributing

We love contributions! Here's how to help:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

See CONTRIBUTING.md for detailed guidelines.

Contributors

• Hasecon - Initial work

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Context7 for inspiration on documentation processing
• MCP Team for the protocol
• Upstash for Redis expertise
• All contributors and community members

📞 Support

• 📖 Documentation
• 🐛 Issues
• 💬 Discussions
• 📧 Email

---