Streamlit Chat App with MCP Integration

A powerful chat application built with Streamlit that integrates with OpenAI's API and Model Context Protocol (MCP) for enhanced tool capabilities.

Features

• 💬 Interactive chat interface with Streamlit
• 🧠 OpenAI API integration with model selection
• 🛠️ MCP server management and tool integration
• ⚡ Both streaming and non-streaming response modes
• 🔄 Automatic tool discovery and invocation

Installation

1. Clone the repository:

git clone https://git.bhakat.dev/abhishekbhakat/mcpapp.git
cd mcpapp

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies:

pip install -e .

Configuration

1. Copy the sample config files:

cp config/sample_config.ini config/config.ini
cp config/sample_mcp_config.json config/mcp_config.json

2. Edit config/config.ini with your OpenAI API key and preferences:

[openai]
api_key = your_api_key_here
base_url = https://api.openai.com/v1
model = gpt-3.5-turbo

[dolphin-mcp]
servers_json = config/mcp_config.json

3. Configure MCP servers in config/mcp_config.json:

{
    "mcpServers": {
        "example-server": {
            "command": "uvx",
            "args": ["mcp-server-example"],
            "env": {
                "API_KEY": "your-api-key"
            }
        }
    }
}

Usage

Start the application:

uv run mcpapp

The app will be available at http://localhost:8501

Architecture

Key components:

• src/app.py: Main Streamlit application
• src/openai_client.py: OpenAI API client with MCP integration
• src/mcp_manager.py: Synchronous wrapper for MCP server management
• src/custom_mcp_client/: Custom MCP client implementation

Development

### Code Formatting
```bash
ruff check . --fix

Building

uv build

License

MIT License - See LICENSE for details.