Model Context Protocol (MCP) Server

@shaswata-das

About Model Context Protocol (MCP) Server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "basic-mcp-server-shaswata-das": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Model Context Protocol (MCP) Server?

A modular Model Context Protocol server for AI services that supports multiple AI providers (Claude, OpenAI, and a mock service) and transport options (stdio, TCP, and WebSocket). It provides a JSON‑RPC 2.0 interface for tool calling and resource management, with dynamic service selection on a per‑request basis.

How to use Model Context Protocol (MCP) Server?

Clone the repository, create a virtual environment, install dependencies with pip install -e ., and configure API keys via the .env file. Run the server with python mcp_server.py (defaults to stdio mode) or use --tcp or --websocket flags to choose other transports. Interact using the provided example clients (examples/example_client.py and examples/websocket_client.html).

Key features of Model Context Protocol (MCP) Server

Multiple AI services (Claude, OpenAI, mock) selectable per request
Three transport options: stdio, TCP, and WebSocket
JSON‑RPC 2.0 compliant interface for predictable interactions
Dynamic service selection without restarting the server
Streaming response support for compatible transports
Modular architecture for easy extension with new services and transports
Qdrant vector database integration for embeddings and semantic search

Use cases of Model Context Protocol (MCP) Server

Build AI‑powered command‑line tools that can switch between models at runtime
Integrate AI assistants into web browsers using WebSocket transport
Test and develop AI workflows locally with the mock service, then swap in real APIs
Deploy a single server that serves multiple AI backends behind a load balancer