abhishekbhakat
80ba05338f
- Added `process.py` for managing MCP server subprocesses with async capabilities. - Introduced `protocol.py` for handling JSON-RPC communication over streams. - Created `llm_client.py` to support chat completion requests to various LLM providers, integrating with MCP tools. - Defined model configurations in `llm_models.py` for different LLM providers. - Removed the synchronous `mcp_manager.py` in favor of a more modular approach. - Established a provider framework in `providers` directory with a base class and specific implementations. - Implemented `OpenAIProvider` for interacting with OpenAI's API, including streaming support and tool call handling.
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
- Clone the repository:
git clone https://git.bhakat.dev/abhishekbhakat/mcpapp.git
cd mcpapp
- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
- Install dependencies:
pip install -e .
Configuration
- Copy the sample config files:
cp config/sample_config.ini config/config.ini
cp config/sample_mcp_config.json config/mcp_config.json
- Edit
config/config.iniwith 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
- 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:
streamlit run src/app.py
The app will be available at http://localhost:8501
Architecture
Key components:
src/app.py: Main Streamlit applicationsrc/openai_client.py: OpenAI API client with MCP integrationsrc/mcp_manager.py: Synchronous wrapper for MCP server managementsrc/custom_mcp_client/: Custom MCP client implementation
Development
Running Tests
pytest
Code Formatting
ruff check . --fix
Building
python -m build
License
MIT License - See LICENSE for details.