MCP (Model Context Protocol)

A Simple Model Context Server For AI

Catalog onlyCatalog onlySTDIO

Overview

MCP (Model Context Protocol) is a standardized protocol developed by Anthropic that enables large language models (LLMs) to interact with external tools and functions, facilitating the injection of context into LLMs.

To use MCP, set up the server by creating a directory, initializing a Node.js project, and installing the Model Context Protocol SDK. Configure the MCP server in your IDE and create a JSON configuration file to define the server settings.

Standardized interaction for LLMs with external tools - Real-time information requests - Execution of actions in external systems - Access to specialized knowledge and APIs

Integrating LLMs with various APIs for enhanced functionality.
Enabling real-time data retrieval for AI applications.
Facilitating complex interactions between AI agents and external systems.

Add to your AI client

Use these steps to connect MCP (Model Context Protocol) 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-kabragaurav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

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-kabragaurav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-kabragaurav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

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-kabragaurav": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-kabragaurav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-kabragaurav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-kabragaurav"
      ]
    }
  }
}

FAQ

What is the purpose of MCP?

MCP standardizes how LLMs interact with external tools, reducing the chances of API breakage and improving integration.

Is MCP easy to set up?

Yes! The setup involves simple steps using Node.js and the Model Context Protocol SDK.

Can MCP be used with any LLM?

Yes! MCP is designed to work with various large language models.

Research and data