MCP Hub is a comprehensive framework for building, managing, and deploying Model Context Protocol (MCP) clients and servers. It provides tools and
MCP Hub is a comprehensive framework for building, managing, and deploying Model Context Protocol (MCP) clients and servers. It provides tools and configurations to
For more details, visit the UV GitHub repository.
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.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| jupyterhub_config.py | Configuration for JupyterHub. |
| start_jupyterhub.sh | Script to start the JupyterHub server. |
| 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. |
| 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. |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Long-term memory for AI agents that actually works.
An MCP server for academic literature workflows in Claude, Cursor, and other MCP clients.
Combine extras with comma separation, e.g. `pip install 'pretensor[postgres,clustering]'`.
SSE-based server hosted on AWS. Just add URL + token to your AI client.