- Home
- MCP servers
- AXYS MCP Lite
AXYS MCP Lite
- javascript
0
GitHub Stars
javascript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
AXYS MCP Lite is a lightweight Model Context Protocol (MCP) server that enables AI-powered search over both structured data and unstructured content. It lets you perform natural language queries to retrieve relevant information across databases, documents, videos, and more, making it easier for AI assistants to find exactly what you need.
How to use
Connect your MCP-compatible client to AXYS MCP Lite to perform natural language searches across your data sources. You can search structured data sources using ai_search_structured and unstructured content such as documents, videos, and files using ai_search_unstructured. Use validate_connection to verify that the MCP API is reachable and your credentials are valid. Typical workflows include querying for employees in a department, finding specific documents, or locating media files by topic.
How to install
Prerequisites you need before installing AXYS MCP Lite:
# Install the MCP server globally (recommended)
npm install -g axys-mcp-lite
If you prefer to build from source, follow these steps:
# Clone the project
git clone https://github.com/rajesh-siliconvalleycloudit/axys-mcp-lite.git
# Change to the project directory
cd axys-mcp-lite
# Install dependencies
npm install
# Build the project
npm run build
Configuration and startup
Configure your MCP client to connect to AXYS MCP Lite using the provided stdio approach. The client runs the MCP server as a local process and communicates via standard input/output.
# Start the MCP server via npx (example runtime shown in the configuration snippet)
npx -y axys-mcp-lite
Available tools
ai_search_structured
Search structured data sources using natural language queries. Provide a natural language query and you will receive relevant results from structured sources.
ai_search_unstructured
Search unstructured content such as documents, videos, and files using natural language. You can filter by indices and choose to return only file references.
validate_connection
Check the connection to the MCP API to ensure credentials and network access are correct.