MCP Server
This project implements an MCP-compliant server that allows AI models to discover and invoke tools through a standardized protocol. The server is designed to be modular, with each tool implemented as a separate Python module.
Overview
MCP Server is a scalable and modular implementation of the Model Context Protocol (MCP) that enables AI models to discover and invoke tools through a standardized protocol.
To use MCP Server, install the required dependencies using pip install -r requirements.txt, and then run the server with the command python -m src.server.
- Modular architecture allowing easy addition of new tools. - Compliance with the Model Context Protocol for standardized tool invocation. - Built using Python, making it accessible for developers familiar with the language.
- Integrating various AI tools into a single server environment.
- Facilitating communication between AI models and external tools.
- Enabling developers to create and manage custom tools easily.
Add to your AI client
Use these steps to connect MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.
Cursor
Add this to your .cursor/mcp.json file in your project root, then restart Cursor.
.cursor/mcp.json
{
"mcpServers": {
"mcp-server-sampad1990": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}Claude Desktop
Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"mcp-server-sampad1990": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"mcp-server-sampad1990": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"mcp-server-sampad1990": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp-server-sampad1990": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"mcp-server-sampad1990": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-server-sampad1990"
]
}
}
}FAQ
What is the purpose of MCP Server?
MCP Server allows AI models to interact with tools in a standardized way, enhancing their capabilities.
How can I add new tools to the server?
You can add new tools by creating a new Python file in the `src/tools` directory and using the `@tool` decorator.
Is MCP Server open-source?
Yes, MCP Server is available on GitHub and can be modified as per your needs.