ruslanmv

The Model Context Protocol (MCP) is a standardized way to supply context to large language models (LLMs). Using the MCP Python SDK, you can build servers that expose data (resources), functionality (tools), and interaction templates (prompts) to LLM applications in a secure and modular fashion. In this tutorial, we’ll build a simple MCP server in P

We’ll start with a concise “Hello World” demo, then explore both the Admin UI and HTTP API methods, and finally walk through a complete example where we integrate a Watsonx.ai Agent into your gateway.

The watsonx-rag-mcp-server is a server designed for data processing and analysis using AI and machine learning. It provides features for efficiently retrieving and generating information. Implemented in Python, it allows users to customize with their own datasets.

CLI and Flask‑based web application that transforms plain‑English prompts into production‑ready, multi‑agent AI workflows. It generates native YAML for IBM WatsonX Orchestrate, Python code for CrewAI, CrewAI Flow, LangGraph, or ReAct, and includes a built‑in FastAPI MCP server wrapper for seamless deployment to the MCP Gateway.

This project is an AI engine that brings a single photo to life, creating a realistic "talking head" video from just an audio file. It's built for flexibility, offering two ways to use it: a standard web API for easy integration into any application, and a specialized server that automatically connects to "MCP Gateway" systems.