mschwarzmueller_demo_mcp_server_client_implementat
by mschwarzmuellerAI Chatbot Integration with MCP Server
Overview
This project demonstrates the implementation of an MCP server that integrates with a basic AI chatbot client. The MCP server consumes a dummy API and exposes it in a standardized way to MCP clients, enabling seamless communication between the chatbot and the backend service. The project is built using Node.js with TypeScript support, requiring Node.js 23.x or higher.
Tools
- Node.js: Modern Node.js with built-in TypeScript support (version 23.x or higher).
- TypeScript: Used for both server and client implementations.
- OpenAI API: Powers the AI chatbot functionality.
Configuration
To set up the project, follow these steps:
- Environment Variables:
-
Add a
.envfile inside theclientfolder with the following content:
plaintext OPENAI_API_KEY=<your-open-ai-key> -
Dependencies:
- Navigate to each folder (
service,server,client) and runnpm installto install the required dependencies.
Usage
Running the Service, MCP Server & MCP Client
- Start the Service:
-
Navigate to the
servicefolder and run:
bash npm run dev -
Start the MCP Server:
-
Navigate to the
serverfolder and run:
bash npm run dev -
Start the MCP Client:
- Navigate to the
clientfolder and run:
bash npm run dev
The AI chatbot client will now be able to interact with the backend service via the MCP server, storing and retrieving custom information as needed.
About
This project is a basic demo implementation of an MCP server and client, showcasing how an AI chatbot can leverage MCP protocols to communicate with backend services. It is designed for educational purposes and may contain bugs.
Resources
License
This project is licensed under the MIT License.
Project Stats
- Stars: 11
- Forks: 5
- Watchers: 1
Languages
- TypeScript: 100.0%
Invite Gmail Contacts
