MCP Code Agent With OpenAI LLMs

📘 Overview

This project implements an AI agent powered by OpenAI's LLMs, designed to interact with the MCP server to access various tools and resources. I plan to add support for the code actions, but currently it is in progress.

📦 Installation

First, ensure you have Poetry installed.

poetry install

🚀 Running the Project

1. Ensure Docker is Running
Make sure the Docker daemon is active on your system. You can check this by running:

   docker info

   

If Docker is not installed, follow the official Docker installation guide for your operating system.

2. Start the MCP Weather Server
Launch the weather server using:

   poetry run poe weather_server

   

3. Run the Chainlit Application
Start the Chainlit app with:

   poetry run poe app

   

Development Setup

This project uses pre-commit to ensure consistent code quality before commits.

poetry run pre-commit install

To manually run hooks:

poetry run pre-commit run --all-files

🛠 Available Tasks

Poe the Poet is used to define common development tasks.

You can list available tasks using:

poetry run poe --help

Defined Tasks

| Task | Description | |------------|----------------------------------------------| | lint | Runs ruff to lint and auto-fix code | | typecheck| Runs mypy for static type checking | | check | Runs both lint and typecheck | | app | Runs the Chainlit application |

Run a task like:

poetry run poe check

📝 License

This repository is licensed under the Apache License, Version 2.0. See the LICENSE file for details.