AXYS MCP Lite
A Model Context Protocol (MCP) server that provides AI-powered search capabilities, enabling AI assistants like Claude to search through structured and unstructured data using natural language commands.
Features
AI-Powered Structured Search: Natural language queries on structured databases
AI-Powered Unstructured Search: Search documents, videos, and files using natural language
Semantic Search: AI understands context and meaning for better results
Multiple Content Types: Search PDFs, Word documents, videos, images, and more
Secure Authentication: API key-based authentication for secure access
Prerequisites
Node.js 18 or higher
MCP API key
Claude Desktop application or any MCP-compatible client
Installation
Via npm (Recommended)
From Source
Quick Start
1. Get Your MCP API Key
Contact your administrator to obtain your MCP API key.
2. Configure Claude Desktop
Add this configuration to your Claude Desktop config file:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%\Claude\claude_desktop_config.json
3. Restart Claude Desktop
Restart Claude Desktop to load the MCP server. You should now be able to use the AI search commands!
Available Tools
1. ai_search_structured
Search structured data sources using natural language.
Parameters:
query(required): Natural language query
Example:
2. ai_search_unstructured
Search documents, videos, and files using natural language.
Parameters:
query(required): Natural language querysearchIndices(optional): Specific index to search (e.g., 'video', 'document')fileOnly(optional): Return only file references without content
Example:
3. validate_connection
Validate connection to MCP API.
Usage Examples
Structured Search
Unstructured Search
Configuration Options
Environment Variables
Create a .env file in your project directory:
Development
Running Locally
Project Structure
Troubleshooting
Connection Issues
Verify
AXYS_API_HOSTURL is correctCheck MCP_KEY is valid and active
Ensure network connectivity to the API server
No Results
Try rephrasing your query
Check if the data exists in the system
Verify your API key has appropriate permissions
API Response Codes
Code | Description |
200 | Success |
201 | AI Tool not configured |
401 | Invalid API Key |
402 | Bad Request |
500 | Internal Server Error |
Security Best Practices
Never commit API keys to version control
Use environment variables for sensitive configuration
Regularly rotate API keys for security
Monitor API usage for unusual activity
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository
Create your feature branch (
git checkout -b feature/AmazingFeature)Commit your changes (
git commit -m 'Add some AmazingFeature')Push to the branch (
git push origin feature/AmazingFeature)Open a Pull Request
Support
For issues:
MCP Server: Open an issue
MCP Protocol: MCP Documentation
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
Built with Model Context Protocol SDK
Designed for use with Claude Desktop and other MCP clients
Changelog
Version 1.0.0
Initial release
AI-powered structured search
AI-powered unstructured search (documents, videos, files)
Connection validation tool
Made with care for the MCP community