Provides access to product management tools and resources via GitHub Copilot integration.
Supports database operations for product management, including inserting and fetching products.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Products Server add a new product named 'Wireless Mouse' with price $25.99"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A hands-on Python project demonstrating Model Context Protocol (MCP) by building a product management server that integrates with Claude Desktop and GitHub Copilot.
create_new_mcp/
ā
āāā mcp_server.py # MCP Server with tools, resource, and prompt template
āāā add_product.py # DB logic to INSERT a product
āāā fetch_products.py # DB logic to SELECT all products
āāā db_connect.py # Database connection helper
āāā .env # API keys and DB credentials (not committed)
āāā .gitignore
āāā README.mdRelated MCP server: ClickUp MCP Server
mcp_server.pyUpdate claude_desktop_config.json:
{
"mcpServers": {
"products": {
"command": "uv.exe",
"args": [
"--directory", "C:\\path\\to\\create_new_mcp",
"run", "mcp_server.py"
]
}
}
}Update mcp.json with the same server details.
Python 3.10+
uv package manager
MySQL database
Claude Desktop or GitHub Copilot
ā MCP Tools are invoked directly by the LLM
ā MCP Resources are fetched manually via host UI and injected into context
ā
Prompt Templates enable consistent prompt generation via / command
ā ļø MCP Sampling (server ā LLM callback) is not yet supported by Claude Desktop or GitHub Copilot in practice
š” Workaround for sampling: call Anthropic API directly from the MCP server
This server cannot be deployed
Manage product translations from Claude and ship reviewed changes as GitHub pull requests.
Bring meeting decisions, tasks and user stories into your AI editor (Claude, Cursor, Copilot).
Manage product ideas, decisions, and customer signals from AI assistants with NLQ
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.