Flex MCP Agent

Flex MCP Agent is a multi - functional agent project that integrates weather data acquisition, Confluence interaction, and email sending functions, standardizing the interaction between AI models and data sources using the Model Context Protocol (MCP).

Artificial intelligence chatbots Knowledge management and memory #AI agent #Protocol standard #Data integration #Multi - service .Python

rating : 2 points

downloads : 12

update time : 2025-04-28

What is Flex MCP Agent?

Flex MCP Agent is an intelligent assistant that can help you query the weather, send emails, and interact with the Confluence document system. It uses the Model Context Protocol (MCP) standard protocol, which acts like a 'universal interface' for AI applications, enabling different systems to work together securely and efficiently.

How to use Flex MCP Agent?

Simply talk to the Agent in natural language, and it will automatically understand your needs and call the corresponding services. For example, say 'Query the weather in Beijing' or 'Send an email to Zhang San', and the Agent will complete the corresponding operations.

Use cases

Suitable for individuals or teams that need to automate daily tasks, especially users who often need to query data, send notifications, or manage documents. Typical scenarios include: automatically sending daily weather briefings, automatically archiving meeting minutes to Confluence, and sending email reminders for important matters, etc.

Main features

Weather queryObtain real - time weather data for any location globally through the Open - Meteo API, including key indicators such as temperature and precipitation probability.

Email sendingIntegrates the SendGrid service, which can quickly send formatted HTML emails, supporting attachments and mass - mailing functions.

Confluence interactionConnects to the enterprise knowledge base system, allowing you to query, create, or edit Confluence document content.

MCP standardized protocolAdopts a unified interface specification to ensure secure and reliable communication between different services and supports future function expansion.

Advantages and limitations

Advantages

Integrates multiple commonly used services in one stop, eliminating the need to switch between different platforms

Uses natural language interaction, with a low usage threshold

Based on the MCP protocol, the system has strong scalability

Open - source architecture, allowing you to customize functions according to your needs

Limitations

Requires initial configuration of parameters such as API keys

Some advanced functions require technical knowledge for customization

Depends on the availability of third - party services (such as SendGrid)

Currently only supports English interaction

How to use

Environment preparation

Install the Python 3.8+ runtime environment. It is recommended to use a virtual environment.

Install dependencies

Install the required software packages via pip.

Configure parameters

Copy the example configuration file and fill in your actual parameters.

Start the service

Start each functional module as needed.

Run the main program

Start the main program of the Agent to start interacting.

Usage examples

Weather query before a business tripQuickly understand the weather conditions at the destination before a business trip and arrange luggage reasonably.

Sending meeting notificationsSend meeting invitations to team members in batches.

Frequently Asked Questions

Which third - party services need to be registered?

How to verify if the service is running normally?

Does it support Chinese interaction?

How is data security ensured?

Related resources

Open - Meteo API documentation

Official documentation for the weather data interface

SendGrid usage guide

Detailed guide for the email sending service

MCP protocol specification

Technical specification for the Model Context Protocol

Project GitHub repository

Get the latest source code and submit issues

🚀 Flex MCP Agent

A proxy integrating weather data retrieval, Confluence interaction, and email sending capabilities. It interacts with users through a structured chat agent and performs tasks based on user input. This project utilizes the Model Context Protocol (MCP) to standardize the interaction between the agent and its data sources.

🚀 Quick Start

The Flex MCP Agent is a versatile tool that combines multiple functions. It uses the Model Context Protocol (MCP) to streamline interactions with data sources. Here's how you can get started with this project.

✨ Features

Weather Data Retrieval: The agent can fetch current weather data for a specified location.
Email Sending: It can send emails using the SendGrid service.
Confluence Integration: The agent can interact with the Confluence platform.
Standardized Interaction: Utilizes the Model Context Protocol (MCP) to standardize communication with data sources.

📦 Installation

Clone the repository

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

Create a virtual environment

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

Install dependencies
```
pip install -r requirements.txt
```
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.
Run 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, refer to my other Git repositories for cloning and configuration.
Run the agent
```
python mcp_agent.py
```

💻 Usage Examples

Basic Usage

Weather Data: The agent can get the current weather data for a location with specified coordinates.
Email Sending: The agent can send emails using the SendGrid service.
Confluence Integration: The agent can interact with the Confluence platform.

📚 Documentation

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's like the USB - C port for AI applications, offering a standardized way to connect AI models with various data sources and tools. This protocol enables seamless integration between data sources and AI - driven tools through a secure two - way connection.

Project Structure

Property	Details
`mcp_weather_server.py`	A server that uses the Open - Meteo API to provide weather data.
`mcp_email_server.py`	A server that uses the SendGrid API to send emails.
`mcp_agent.py`	The main script of the agent, responsible for initializing the agent, loading configurations, and handling user input.
`prompt.py`	A file containing the agent's system prompts, guiding its behavior and responses.
`config.example.json`	An example configuration file for setting server URLs and transport methods.
`requirements.txt`	Lists the Python dependencies required for the project.
`.env.example`	An example environment file for setting necessary environment variables.