HoangYell/simple-mcp-vscode
If you are the rightful owner of simple-mcp-vscode and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Model Context Protocol (MCP) server is a customizable server that allows users to interact with language models through a structured protocol, enabling enhanced communication and tool integration within development environments like VS Code.
Create a Custom MCP Server and Use It with GitHub Copilot in VS Code
Description: Basic example for using Model Context Protocol (MCP) with VS Code. This repo shows how to create your own MCP server and interact with it by chatting custom prompts to GitHub Copilot in VS Code.
- Clone & enter the repo
git clone git@github.com:HoangYell/simple-mcp-vscode.git
cd simple-mcp-vscode
- (If needed) Install venv module
sudo apt install python3-venv
- Create & activate a virtual environment
python3 -m venv .venv
source .venv/bin/activate
- Install dependencies
pip install -r requirements.txt
- Configure VS Code
Add to your :
{
"chat.mcp.discovery.enabled": true,
"mcp": {
"servers": {
"SimpleMCP": {
"type": "python",
"command": "/path/to/project/.venv/bin/python", // e.g. /home/hoangyell/simple-mcp-vscode/.venv/bin/python
"args": ["/path/to/project/server.py"], // e.g. /home/hoangyell/simple-mcp-vscode/server.py
"cwd": "/path/to/project" // e.g. /home/hoangyell/simple-mcp-vscode
}
}
}
}
- Click
above SimpleMCP in VS Code's settings, or run:
python server.py
- Try it!
- In the chat, type:
who the fuck is hoangyell? - Or:
who the fuck is yellshark?
You should now see the MCP tools working in VS Code chat.
https://www.youtube.com/watch?v=U1YMyUdjqCw
MCP Data Flow Overview (ASCII Art):
User VS Code (MCP Client, "chat.mcp.enabled": true) LLM Server (e.g. Copilot/GPT) MCP Server
| | | |
| 1. "Who the fuck | | |
| is yellshark?" | | |
|----------------------------->| | |
| | 2. Send prompt to LLM | |
| |------------------------------------------->| |
| | | 3. Parse intent, |
| | | select tool: |
| | | who_the_fuck_is_yellshark() |
| | 4. Return tool call info | |
|<-----------------------------|<-------------------------------------------| |
| 5. Call tool: | | |
| who_the_fuck_ | | |
| is_yellshark() |------------------------------------------->| |
| | | 6. Execute tool |
| | |--------------------------------------->|
| | | |
| | | 7. Return tool output |
| |<-------------------------------------------|<---------------------------------------|
| 8. Display result in chat UI | | |