Simple MCP Build

This project implements the Model Context Protocol (MCP) framework for dynamic management of query routing and execution context, supporting climate data analysis.

Research and data Developer tools #Dynamic Routing #Context Management #Climate Analysis .Python

rating : 2.5 points

downloads : 5

update time : 2025-04-29

What is MCP Framework?

The Model Context Protocol (MCP) Framework is a specialized tool designed for climate data analysis. It helps researchers and analysts process climate-related datasets through a structured pipeline, while maintaining context memory across executions.

How to use MCP Framework?

The framework is executed through a simple command line interface after setting up the Python environment. Configuration is managed through YAML files, making it accessible even for non-programmers.

Use Cases

Ideal for climate research teams needing to analyze temperature trends, run scenario projections, or process multiple climate datasets with consistent context tracking.

Key Features

Dynamic Query RoutingAutomatically directs queries to appropriate processing modules based on content and context

Execution Context MemoryMaintains memory of previous executions for consistent analysis context

Modular ArchitectureEasy to extend with new analysis modules without modifying core framework

Configuration-DrivenPipeline behavior controlled through simple YAML configuration files

Pros and Cons

Advantages

Simplifies complex climate data analysis workflows

Maintains consistent context across multiple executions

Easy to configure without programming knowledge

Modular design allows for custom extensions

Limitations

Currently focused on climate data analysis (limited to specific use cases)

Requires Python environment setup

Limited documentation for advanced customization

Getting Started

Set up environment

Create and activate a Python virtual environment

Install dependencies

Install required Python packages

Configure pipeline

Edit the config.yaml file to specify datasets and processing steps

Run analysis

Execute the main pipeline

Example Use Cases

Temperature Trend AnalysisAnalyze historical temperature data to identify trends

Climate Scenario ProjectionRun future climate scenarios based on different models

Frequently Asked Questions

Do I need programming skills to use MCP?

Where can I find example configurations?

How do I add my own analysis models?

Additional Resources

GitHub Repository

Source code and issue tracking

Python Virtual Environments Guide

Official Python documentation on virtual environments

YAML Configuration Tutorial

Official YAML specification and examples

🚀 Model Context Protocol (MCP) Implementation

This repository contains the Model Context Protocol (MCP) framework being developed by ClimateGPT Team 1. The MCP framework aims to provide a structured approach for managing model contexts and executing related tasks.

🚀 Quick Start

📂 Project Structure

/mcp-framework
    ├── modules/                     # Core MCP components
    │   ├── context_manager.py       # Store execution context memory
    │   ├── data_loader.py           # Handle dataset loading
    │   ├── query_manager.py         # Dynamically route queries
    │   ├── pipeline_manager.py      # Execute MCP steps
    ├── models/                      # Test EDA / Initial models for MCP framework inspection
    │   ├── scenario_projection.py   # Temperature trend analysis
    │   ├── temperature_trends.py    # Climate scenario projection
    │   ├── Model3.py                # Model 3
    ├── config/                      # Configuration settings
    │   ├── config.yaml              # Define dataset paths and pipeline steps
    ├── logs/                        # Execution logs
    │   ├── mcp_execution.log
    ├── tests/                       # Unit tests for MCP validation
    ├── main.py                      # Entry point for MCP execution
    ├── requirements.txt             # Python dependencies
    ├── README.md                    # Project documentation

How to Run the MCP Framework

Clone the repository (if not already cloned):

git clone https://github.com/newsconsole/GMU_DAEN_2025_01_A.git

Switch to the ClimateGPT Team 1 branch:

git checkout ClimateGPT_Team1

Ensure the virtual environment (venv) is set up:

1. python -m venv venv
2. venv\Scripts\Activate

Install dependencies (requirements.txt):

pip install -r requirements.txt

Run the MCP pipeline:

python main.py

📚 Documentation

Configuration and Execution

The MCP pipeline is dynamically controlled by config/config.yaml, which defines the datasets and pipeline steps.
Logs are stored in logs/mcp_execution.log for debugging and tracking execution results.