Flex MCP Agent

Agent that integrates weather data retrieval, Confluence interaction and email sending functionalities. It uses a structured chat agent to interact with users and perform tasks based on user input. The project leverages the Model Context Protocol (MCP) to standardize interactions between the agent and various data sources.

Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs). It acts like a USB-C port for AI applications, providing a standardized way to connect AI models to various data sources and tools. This protocol enables secure, two-way connections between data sources and AI-powered tools, facilitating seamless integration and interaction.

Project Structure

• mcp_weather_server.py: A server that provides weather data using the Open-Meteo API.
• mcp_email_server.py: A server that sends emails using the SendGrid API.
• mcp_agent.py: The main agent script that initializes the agent, loads configurations, and handles user input.
• prompt.py: Contains the system prompt for the agent, guiding its behavior and responses.
• config.example.json: An example configuration file for setting up server URLs and transports.
• requirements.txt: Lists the Python dependencies required for the project.
• .env.example: An example environment file for setting up necessary environment variables.

Setup Instructions

1. Clone the Repository

   git clone git@github.com:MahithChigurupati/Flex-MCP-Agent.git
   cd Flex-MCP-Agent
   

2. Create a Virtual Environment

   python3 -m venv .venv
   source .venv/bin/activate
   

3. Install Dependencies

   pip install -r requirements.txt
   

4. Configuration

   • Copy config.example.json to config.json and update the URLs and transport methods as needed.
   • Copy .env.example to .env and fill in the required environment variables, such as SENDGRID_API_KEY and FROM_EMAIL.

5. Running the Servers

   • Start the weather server:

     python mcp_weather_server.py
     

   • Start the email server:

     python mcp_email_server.py
     

   • For the Confluence MCP server, please check my other Git repository to clone and set it up.

6. Running the Agent

   python mcp_agent.py
   

Usage

• Weather Data: The agent can fetch current weather data for specified coordinates.
• Email Sending: The agent can send emails using the SendGrid service.
• Confluence Integration: The agent can interact with Confluence using available tools.

Environment Variables

• SENDGRID_API_KEY: API key for SendGrid.
• FROM_EMAIL: The email address from which emails will be sent.
• OPENAI_MODEL: The model name for OpenAI's language model.

Dependencies

The project requires the following Python packages:

• langchain_mcp_adapters
• langchain_openai
• langchain
• python-dotenv
• sendgrid