MCP Hub is a framework for creating and managing Model Context Protocol (MCP) servers and clients. It leverages the uv tool for fast package installation and configuration management.
UV simplifies package management and configuration with blazing-fast commands. Learn a few commands to get started, and you're good to go:
- Initialize a project:
uv init
- Sync Python version and dependencies:
uv sync
For more details, visit the UV GitHub repository.
To understand the basics of MCP and get started with creating MCP servers, refer to the MCP Quickstart Server Guide.
-
Create a New Project Directory
uv init XYZ cd XYZ -
Set Up a Virtual Environment
uv venv source .venv/bin/activate -
Install Dependencies
uv add "mcp[cli]" httpx -
Create the Server File
touch XYZ.py
To run the server, use the following command:
uv run XYZ.pyFollow the steps outlined above to create and run a new XYZ server. Replace XYZ with your desired project name.
The notebooks/ directory has been added to the project. It includes configuration files and scripts for setting up and running JupyterHub. Key files include:
jupyterhub_config.py: Configuration for JupyterHub.start_jupyterhub.sh: Script to start the JupyterHub server.
A new script has been added under ai/computer-vision/09_datasets/ to download the CIFAR-10 dataset using TensorFlow/Keras. To use it, run:
python ai/computer-vision/09_datasets/download_cifar10.pyThis script downloads the dataset and prints a confirmation message.
The ai/ folder contains various subdirectories and scripts related to computer vision and artificial intelligence. Below is an overview of its structure and contents:
basic_manipulations.py: Basic image manipulation techniques.blue_image.png: Sample image for testing.hello_cv.py: A simple script to demonstrate computer vision basics.image_representation.py: Explains image representation in computer vision.read_display_save.py: Script to read, display, and save images.README.md: Documentation for this subdirectory.
augmentation.py: Image augmentation techniques.normalization.py: Image normalization methods.
hog_extraction.py: Extracts Histogram of Oriented Gradients (HOG) features.sift_surf_extraction.py: Demonstrates SIFT and SURF feature extraction.
hog_svm_classifier.py: Implements a classifier using HOG features and SVM.
cnn_architecture.py: Defines a Convolutional Neural Network (CNN) architecture.
train_classifier.py: Script to train an image classifier.
basic_object_detection.py: Demonstrates basic object detection techniques.
basic_segmentation.py: Explains basic image segmentation methods.
download_cifar10.py: Script to download the CIFAR-10 dataset.
image_utils.py: Utility functions for image processing.
main.py: Entry point for AI-related scripts.pyproject.toml: Configuration file for the project.README.md: Documentation for theai/folder.run.sh: Shell script to execute AI-related tasks.uv.lock: Lock file for dependencies.