mcpField
N
neural-mcp

neural-mcp

Local
andylbrummer.github.ioDeveloper Tools2Updated 26w ago
RepositoryVisit website

About neural-mcp

neural-mcp is an MCP server for building, training, and analyzing neural networks, aimed at machine-learning experimentation. It combines dataset loading, training, evaluation, tuning, and model export, with optional CUDA acceleration.

Key features

  1. 01Build ResNet18, MobileNet, and custom models
  2. 02Load CIFAR-10, MNIST, and ImageNet
  3. 03Train models with configurable parameters
  4. 04Evaluate models and compute metrics
  5. 05Tune hyperparameters automatically
  6. 06Export to ONNX or TorchScript

Use cases

  1. 01Train a model on a standard dataset
  2. 02Experiment with custom network architectures
  3. 03Measure model performance and inspect predictions
  4. 04Export a trained model for another workflow

MCP support

Exposes neural-network model, data-loading, training, evaluation, analysis, tuning, and export tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "andylbrummer-neural": {
      "command": "uvx",
      "args": [
        "scicomp-neural-mcp"
      ]
    }
  }
}
Run commanduvx scicomp-neural-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiscicomp-neural-mcp0.1.6

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

scicomp-neural-mcp

mcp-name: io.github.andylbrummer/neural-mcp

MCP server for neural network training and experimentation.

Overview

This server provides tools for building, training, and analyzing neural networks:

  • Model building - Pre-trained models (ResNet, MobileNet) and custom architectures
  • Dataset loading - CIFAR-10, MNIST, ImageNet datasets with standard preprocessing
  • Training - Full training loops with configurable learning rates and batch sizes
  • Evaluation - Model evaluation, metrics computation, and analysis
  • Hyperparameter tuning - Automated hyperparameter search
  • Export - Export models to ONNX and TorchScript formats
  • GPU acceleration - Optional CUDA acceleration for training

Installation & Usage

# Run directly with uvx (no installation required)
uvx scicomp-neural-mcp

# Or install with pip
pip install scicomp-neural-mcp

# With GPU support (recommended for training)
pip install scicomp-neural-mcp[gpu]

# Run as command
scicomp-neural-mcp

Available Tools

Model Management
  • define_model - Create neural network models (ResNet18, MobileNet, custom)
  • load_pretrained - Load pretrained models from torchvision or Hugging Face
  • get_model_summary - Get detailed layer-by-layer breakdown
  • export_model - Export to ONNX or TorchScript
Data Loading
  • load_dataset - Load standard datasets (CIFAR-10, MNIST, ImageNet)
  • create_dataloader - Create batched dataloaders with shuffling
Training
  • train_model - Train model on dataset with configurable parameters
  • get_experiment_status - Monitor training progress
  • evaluate_model - Evaluate on test set
Analysis
  • compute_metrics - Compute detailed performance metrics
  • confusion_matrix - Generate confusion matrices
  • plot_training_curves - Visualize loss and accuracy curves
  • visualize_predictions - Inspect model predictions on samples
Hyperparameter Optimization
  • tune_hyperparameters - Automated hyperparameter search

Configuration

Enable GPU acceleration with environment variable:

MCP_USE_GPU=1 scicomp-neural-mcp

Examples

📖 Code Examples

Practical tutorials in EXAMPLES.md:

  • MNIST digit recognition (complete workflow)
  • Transfer learning with ResNet
  • Hyperparameter optimization
  • Confusion matrix analysis
  • Progressive learning path (beginner → advanced)
📚 Full Documentation

See the API documentation for complete API reference.

Part of Math-Physics-ML MCP System

Part of a comprehensive system for scientific computing. See the documentation for the complete ecosystem.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.