mcpField
M
Model Context Protocal (MCP) Implementation

Model Context Protocal (MCP) Implementation

Local
github.com/jraa1995Developer Tools1Updated 90w ago
Repository

About Model Context Protocal (MCP) Implementation

A Python framework under development by ClimateGPT Team 1 for configurable data pipelines. It includes context memory, dataset loading, dynamic query routing, and climate analysis models.

Key features

  1. 01Execution context memory
  2. 02Dataset loading
  3. 03Dynamic query routing
  4. 04Configurable pipeline steps
  5. 05Climate scenario models

Use cases

  1. 01Configuring datasets and pipeline steps
  2. 02Running temperature trend analysis
  3. 03Inspecting pipeline execution logs

MCP support

The repository describes a framework called MCP, but does not specify how it relates to the Model Context Protocol.

#mcp#data-exchange#communication

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

Model Context Protocal (MCP) Implementation

This repository includes the Model Context Protocol (MCP) framework that ClimateGPT Team 1 is developing.

📂 Project Structure

/mcp-framework ├── modules/ # Core MCP components │ ├── context_manager.py # Stores execution context memory │ ├── data_loader.py # Handles dataset loading │ ├── query_manager.py # Routes queries dynamically │ ├── pipeline_manager.py # Executes MCP steps ├── models/ # Test EDA / initial models for MCP framework checking │ ├── scenario_projection.py # Temp trend analysis │ ├── temperature_trends.py # Climate scenario projections │ ├── Model3.py # Model 3 ├── config/ # Configuration settings │ ├── config.yaml # Defines 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 MCP Framework

  1. Clone the repository (if not already cloned):

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

  2. Switch to the ClimateGPT Team 1 Branch:

    git checkout ClimateGPT_Team1

  3. Make sure to set up venv (Virtual Env)

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

  4. Install dependencies (requirements.txt):

    pip install -r requirements.txt

  5. Run the MCP Pipeline

    python main.py
Configuration & 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
Recent Updates
  • Implemented initial MCP Framework with modular design
  • Added dynamiic query routing & context memory

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.