MCP_Integration_Package-NPM
A lightweight, production-ready Model Context Protocol (MCP) server for exposing Node.js functions to Claude Desktop and other AI agents via JSON-RPC 2.0 over STDIO.
claude mcp add --transport stdio myat-kyaw-thu-mcp_integration_package-npm mcp-connect path/to/your/mcp.config.js
How to use
This MCP server is powered by the mcp-connect CLI. It reads a local mcp.config.js file (created via mcp-connect init) that defines the tools your app exposes to AI agents. Each tool is a simple named function, for example hello(name) and echo(message), and you can expand this with more complex handlers, validation, and schemas as shown in the CLI usage examples. To use it with Claude Desktop or other clients, start the server with the mcp-connect command pointing at your config, then connect the client by referencing the server’s tools. Tools can be invoked by name with the expected parameters, and the results are returned to the AI agent for natural language processing and decision making.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Basic familiarity with the command line
Step-by-step installation:
-
Install the MCP CLI globally npm install -g @myatkyawthu/mcp-connect
-
Create a sample config (runs from your project directory)
Navigate to your project directory
cd your-project
Generate sample config
mcp-connect init
This creates mcp.config.js with example tools such as hello and echo
-
Run the MCP server mcp-connect /path/to/your/mcp.config.js
Notes:
- You can customize your tools by editing mcp.config.js to add more tools, validation, and descriptions.
- The example config uses defineMCP from @myatkyawthu/mcp-connect to declare tools.
Additional notes
Tips and common issues:
- Ensure the path to mcp.config.js is absolute when configuring clients (Claude Desktop or others).
- If Claude Desktop fails to connect, restart Claude Desktop and verify the config path and file permissions.
- When adding tools, start with simple ones to verify the basic request/response flow before scaling to more complex schemas.
- The mcp.config.js should export a default defined via defineMCP, listing tools as either simple ["name", async (...) => ...] entries or more advanced objects with validation and schemas.
- If you upgrade the MCP package, re-run any necessary build or type-check steps in your project.
Environment variables (optional):
- No required environment variables are strictly needed for the basic setup. You may introduce custom env vars in your hosting environment and access them within tool handlers if needed.
Related MCP Servers
mcp-for-beginners
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
anki
MCP server for anki
openai -agent-dotnet
Sample to create an AI Agent using OpenAI models with any MCP server running on Azure Container Apps
unity-editor
An MCP server and client for LLMs to interact with Unity Projects
create -kit
Scaffold a production-ready Model Context Protocol (MCP) server in seconds.
Lite_MCP_sdk
a light weight version of mcp sdk inspired by official model context protocol sdk, NOW focus on sse only no stdio