Pydantic Ai MCP Agent With Chainlit

🚀 AI Agent MCP Agent with Pydantic and Chainlit

A powerful AI agent implementation using Pydantic and Chainlit, integrating MCP (Multi-Command Protocol) for web browsing and interaction.

✨ Features

• Web browsing with automated interaction.
• Integration with Ollama to support local large language models.
• Interactive chat interface based on Chainlit.
• Type-safe data processing using Pydantic models.
• Configurable MCP server integration.

📦 Installation

Prerequisites

• Python 3.8+
• Node.js and npm (for the MCP server)
• Ollama installed locally
• Access to the MCP server

Steps

1. Clone the repository:

git clone https://github.com/RyanNg1403/pydantic-ai-mcp-agent-with-chainlit.git
cd pydantic-ai-mcp-agent-with-chainlit

2. Install Python dependencies:

pip install -r requirements.txt

3. Install Node.js dependencies:

npm install

📚 Documentation

Configuration

1. Copy the configuration file template:

cp mcp_config.template.json mcp_config.json

2. Use a text editor to modify mcp_config.json and fill in the configuration information according to your actual needs. This file is ignored by Git for security reasons.

Usage

Run the Chainlit interface:

chainlit run pydantic_mcp_chainlit.py

Run the agent directly:

python pydantic_mcp_agent.py

Project Structure

• pydantic_mcp_agent.py: Core agent implementation file.
• pydantic_mcp_chainlit.py: Chainlit interface implementation file.
• mcp_client.py: MCP client implementation file.
• requirements.txt: List of Python dependencies.
• mcp_config.template.json: Configuration file template.
• .gitignore: Specifies files to be ignored by Git.

Environment Variables

Set the following environment variables in the .env file:

• EXA_API_KEY: Your MCP API key.
• OLLAMA_HOST: Ollama service address (default is http://localhost:11434).

🤝 How to Contribute

1. Fork the project repository.
2. Create a feature branch (e.g., git checkout -b feature/amazing-feature).
3. Commit your changes (e.g., git commit -m 'Add amazing feature').
4. Push the branch to the remote repository (e.g., git push origin feature/amazing-feature).
5. Submit a Pull Request.