The classification of music genres plays a crucial role in modern digital audio signal processing applications. In this study, we propose several machine learning approaches to accurately categorize music tracks into predefined genres. Each approach uses different sets of features that can be extracted from songs; ranging from common ones like MFCC (Mel-frequency cepstral coefficients) and direct audio signals to less explored features in this context such as song lyrics and Wavelet Transform. To evaluate the models, we use the GTZAN reference dataset in the field. The results obtained highlight that song lyrics do not contribute much to classification, at least in the dataset used. The other models show results consistent with the state of the art, with an accuracy between 75% and 80%.

• Machin Learning / Artificial Intelligence | Python
• Models: CNN, RNN
• Keywords: Music genre, CNN, spectrograms, MFCC, Conv1D, encoder

In this project, the problem of precise image retrieval is addressed. The work employs a new approach: the application of the Segment Anything (SAM) segmentation models and the Constractive Language-Image Pretraining (CLIP) model for the generation of multimodal embeddings. Special emphasis is placed on image retrieval via precise queries, taking into account the position of image segments that compose the same, processing both text and images.

• IRS / ML / AI | Python
• Keywords: Embeddings, Multimodals Embeddings

The MCP Ecosystem serves as a centralized hub for projects built around the Model Context Protocol (MCP), an open standard designed to seamlessly connect artificial intelligence applications with external data sources, tools, and services. This repository consolidates a diverse set of tools, servers, and client libraries that implement or extend MCP, making it easier for developers and organizations to integrate AI models with real-world data and functionalities.

By providing reference implementations, modular components, and standardized interfaces, the MCP Ecosystem accelerates the adoption of MCP in both research and production environments. Whether you are building custom AI agents, deploying secure MCP servers, or experimenting with new integration protocols, this collection offers practical resources to streamline development and foster interoperability.

Key features of the MCP Ecosystem include:

• A curated set of repositories covering client libraries, authentication systems, server implementations, and integration templates.
• Emphasis on security, extensibility, and adherence to MCP standards.
• Comprehensive documentation and active community support to facilitate onboarding and collaboration.

The MCP Ecosystem is ideal for anyone seeking to bridge the gap between advanced AI models and the complex landscape of external data and services, enabling scalable, secure, and future-proof integrations.

• Model Context Protocol (MCP)
• Large Language Model (LLM)
• Standart Authorization (OAuth2)
• Full Examples for mcp-client and mcp-server

Python client, based on mcp[cli], for connecting to MCP servers through multiple protocols, specifically designed to work with integrated language models. This package provides a Python interface to connect to MCP servers in an easy, intuitive, and configurable way. It offers a modular architecture that allows for easy extension of new transfer protocols and language models. Currently includes support for HTTPStream and GPT-4 mini, with expansion capability for more options in the future.

• Model Context Protocol (MCP)
• Large Language Model (LLM)

pipx install fastchat-mcp

This project represents a simple and extensible OAuth system in Python, integrated as much as possible with MCP standards and practices. Its goal is to facilitate the use of the OAuth system for MCP. It is integrated with the official MCP Python SDK ("mcp[cli]"), following the source code standard that provides the basis for the entire authorization system used and controlled by FastMCP.

Both an OAuth server and client are implemented, respecting the most common standards to maintain standardization. It is important to highlight that the OAuth server standard in the MCP context is still poorly defined and with scarce documentation, so the greatest possible standardization has been sought both in the server and client code.

This repository starts from the Antropic example in the official repository, modifying and restructuring the code to achieve optimal organization, facilitating practical and easy use when installing this repository as a pip package.

• Model Context Protocol (MCP)
• Authorization (OAuth2)
• MCP Cient
• MCP Server

pipx install mcp-oauth