The my-mcp-server is a Node.js server implementing the Model Context Protocol (MCP) that provides three tools for AI-powered interactions:
Greet: Generate personalized greeting messages by providing a name
Calculate: Evaluate basic mathematical expressions (e.g., 2 + 2)
Weather Info: Retrieve mock weather data for a specified city
Enables access to a GitHub repository containing the MCP server implementation, allowing users to clone the project and use the provided tools.
Provides a simple MCP server implementation in Node.js with three tools: greet for personalized messages, calculate for basic math operations, and weather_info for retrieving mock weather data for cities.
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., "@my-mcp-server what's the weather in Tokyo?"
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 simple Model Context Protocol (MCP) server implementation in Node.js. This server exposes three tools via MCP:
greet: Greet someone with a personalized message.
calculate: Perform basic math calculations.
weather_info: Get mock weather information for a city.
Above ones are implemented in the server1.js
in server2 there is an agent that requires selenium web driver that launches the html provided in prompt in a browser and tests and returns if any console errors are thrown.
All these agents can be used in not just copilot but with other AI extensions too for example refer this video for Amazon Q --> https://www.youtube.com/watch?v=sF6KkaV102M
MCP server using @modelcontextprotocol/sdk
Stdio transport for easy integration
Extensible tool definitions
Related MCP server: HelloWorld MCP Server
Clone the repo and install dependencies
git clone https://github.com/devashish234073/my-mcps
cd my-mcps
npm installOpen the my-mcp folder in vscode
Open copilot chat
In the chat click on "Configure Tools"
Add more tools
Add MCP Server
This creates an mcp.json file with minimal configuration of the command your mcp server will run, in our case the repo already has that so step #4 to #7 is not needed
Just go to that file and click "Restart"
The server.js has three tools greet, calculate and weather_info
You can interact with these now using prompts like:
Perform basic math calculations
Inputs: expression (required).
Greet someone with a personalized message
Inputs: name (required).
Get weather information for a city
Inputs: city (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct and non-overlapping purpose: calculate handles math, greet handles messaging, and weather_info handles weather data. An agent can easily tell them apart with no risk of misselection.
The naming is mixed: calculate and greet are verbs, while weather_info is a noun phrase. There is no consistent verb_noun pattern, but the names are still readable and descriptive.
With only 3 tools, the server feels thin and under-scoped for a general-purpose MCP server. The tools cover unrelated domains (math, greeting, weather), suggesting a lack of cohesive focus.
The server lacks a clear domain, making completeness hard to assess. Each tool stands alone without supporting operations (e.g., no update or delete for weather), leading to significant gaps in any potential workflow.
POC MCP server. Tool say_hello returns 'Welcome' (agent -> MCP -> API path).
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
