mcp-demo
0
The project demonstrates a Model Context Protocol server with Retrieval-Augmented Generation capabilities. It allows AI models to interact with and search a knowledge base, supporting both SSE and stdio communication modes. The server can be customized with additional tools, resources, and prompt templates.
MCP with RAG Demo
This demonstration project showcases a Model Context Protocol (MCP) server with Retrieval-Augmented Generation (RAG) capabilities. The demo enables AI models to interact with a knowledge base, search for information, and add new documents.
Features
- MCP server with tool and resource support
- RAG implementation with in-memory storage fallback
- Client example for server interaction
- Supports SSE (HTTP) and stdio communication modes
- Simple prompt templates
Prerequisites
- Python 3.8+
- pip
Usage
Start the MCP server using SSE or stdio modes and run a client example to communicate with the server. Customize tools, resources, and prompts as needed.
License
The project is provided under the MIT License.