Skip to content

Latest commit

 

History

History
52 lines (33 loc) · 1.88 KB

README.MD

File metadata and controls

52 lines (33 loc) · 1.88 KB

MCP Workshop

This workshop is intended to teach you the basics of the Model Context Protocol (MCP). It will specifically have you do the following:

  • Start a simple chatbot with no interactions
  • Add a simple MCP server to allow the LLM to have access to realtime information
  • Create your own test MCP server

Requirements

Setup

  1. Clone the repository:

    git clone https://github.com/dockersamples/mcp-workshop.git
cd mcp-workshop

  2. Open the project in VS Code

  3. When prompted, click the Reopen in Container button to open the project in a devcontainer.

    Screenshot of the "Reopen in Container" dialog

    • NOTE 1: If you miss the dialog or accidentally close it, you can launch it by going to View -> Command Palette... -> Dev Containers: Reopen in Container

    • NOTE 2: It may take a little while to get started, as multiple container images will be downloaded and built, Python dependencies will be installed, etc. It'll come up soon though!

  4. Copy the chatbot/.env.example file to create a chatbot/.env file.

    cp chatbot/.env.example chatbot/.env

  5. Update the newly created chatbot/.env file and add your API key:

    LLM_SOURCE=openai
IN_CONTAINER=true # doesn't matter unless using ollama
OPENAI_API_KEY=sk-proj-hNHhZ-rest-of-key

You're ready to go! Go to the Workshop Guide to get started with the workshop!

License

This workshop is licensed under the MIT License. Portions of this repo were leveraged from the 3choff/mcp-chatbot project.