FastMCP ML Workflow Server

A comprehensive MCP server providing machine learning tools for drug discovery, molecular analysis, and general data science workflows.

Quick Start

# Install dependencies
pip install -r requirements.txt

# Run the ML workflow MCP server (includes MLflow integration)
python fastmcp_server.py

Usage Examples

Natural Language Examples

ML Workflow with MLflow Tracking:

• "Train a random forest model on this dataset with MLflow tracking"
• "Run the MLflow quickstart demo"
• "Show me my recent MLflow runs"
• "Find the best model from my training experiment"
• "Load my best model for serving"
• "Create a correlation heatmap for my molecular data"
• "Evaluate my trained model and show performance metrics"

Training a Model

from ml_workflow_server.tools.model_training import ModelTrainingTool

tool = ModelTrainingTool()
result = tool.execute(
    data_path="data/chembl_p53.csv",
    target_column="standard_value",
    model_type="random_forest_regressor",
    model_params={"n_estimators": 100, "random_state": 42},
    test_size=0.2
)
print(f"Model saved to: {result['model_path']}")

Creating Visualizations

from ml_workflow_server.tools.data_visualization import DataVisualizationTool

viz_tool = DataVisualizationTool()
result = viz_tool.execute(
    data_path="data/protein_ligand_binding.csv",
    plot_type="correlation_heatmap",
    columns=["binding_affinity", "molecular_weight", "logp"],
    output_path="output/correlation_analysis.png",
    title="Molecular Property Correlations"
)

Model Evaluation

from ml_workflow_server.tools.model_evaluation import ModelEvaluationTool

evaluator = ModelEvaluationTool()
eval_result = evaluator.execute(
    model_path="models/rf_model.pkl",
    test_data_path="data/test_dataset.csv",
    target_column="standard_value", 
    task_type="regression",
    output_dir="evaluation_results/"
)

Claude Desktop Configuration

To use this MCP server with Claude Desktop, add this configuration to your Claude Desktop settings:

{
  "mcpServers": {
    "ml-workflow": {
      "command": "python",
      "args": ["fastmcp_server.py"],
      "cwd": "/your_workspace/MLOps_MCP"
    }
  }
}

Project Structure

mlops-mcp/
├── fastmcp_server.py              # Main MCP server entry point
├── requirements.txt               # Python dependencies
└── ml_workflow_server/            # Core ML workflow package
    ├── tools/                     # ML tool implementations
    │   ├── data_preprocessing.py  # Data cleaning and feature engineering
    │   ├── data_visualization.py  # Advanced plotting and visualization
    │   ├── model_training.py      # ML model training pipeline
    │   └── model_evaluation.py    # Model evaluation and metrics
    └── utils/                     # Shared utilities
        ├── file_utils.py          # File operations and path management
        ├── mlflow_config.py       # MLflow configuration and logging
        └── mlflow_management.py   # MLflow model management