MCP ExplorerExplorer

Azure Terminal Copilot

@madebygpson 9 months ago
16 MIT
FreeCommunity
AI Systems
#azure#mcp#python
A Python-based Azure CLI assistant that provides natural language processing capabilities for Azure commands, leveraging Azure MCP Server.

Overview

What is Azure Terminal Copilot

azure-terminal-copilot is a Python-based Azure CLI assistant that utilizes natural language processing to facilitate Azure command execution, leveraging the Azure MCP Server.

Use cases

Use cases include querying Azure resource groups, automating routine Azure CLI commands, and enhancing user interaction with Azure services through natural language.

How to use

To use azure-terminal-copilot, clone the repository, set up a virtual environment with uv, install the necessary packages, configure the .env file with your local addresses for Ollama and Azure MCP, and run the main script using Python.

Key features

Key features include natural language processing for Azure commands, easy installation through Python package management, and the ability to experiment with different models for improved performance.

Where to use

azure-terminal-copilot can be used in cloud computing environments, particularly for managing Azure resources and automating command execution through natural language queries.

Content

Azure Terminal Copilot

A Python-based Azure CLI assistant that provides natural language processing capabilities for Azure commands, leveraging Azure MCP Server.

console

Prerequisites

Installation

  1. Clone the repo

    git clone https://github.com/yourusername/azure-terminal-copilot.git
    cd azure-terminal-copilot
    
  2. Open the terminal and Start a virtual env with uv

    uv venv
    
  3. Install packages using uv

    uv pip install .
    
  4. Run Ollama and make note of its local address

  5. Run Azure MCP server and make note of its local address

  6. Rename .env-sample to .env

  7. I provided dummy values there so make sure to update with the values that correspond to your locally running ollama, Azure MCP, and model you want to use

  8. Now you can run python main.py

Learning

Once the program is running, try a few things:

  1. Try providing a query like ‘list all my resource groups’, is the command you expect to be executed being ran?
  2. Try different models, notice which ones perform better?
  3. Try tweaking the system prompt, how would you improve it?

Troubleshooting

  • Make sure your azure cli is logged in, azure MCP uses that as auth

License

This project is licensed under the MIT License - see the LICENSE file for details.

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers