LLaMa MCP Streamlit

by Nikunj2003

2 forks

13 stars

Free

What is LLaMa-MCP-Streamlit

LLaMa-MCP-Streamlit is an innovative interactive AI assistant developed by Nikunj2003. This tool leverages the power of Streamlit, NVIDIA NIM's API (LLaMa 3.3:70b)/Ollama, and the Model Control Protocol (MCP) to provide users with a seamless conversational interface. At its core, the server facilitates interactions with a large language model (LLM) that can execute real-time external tools via MCP, retrieve data, and perform a variety of actions efficiently. The assistant is designed to enhance user experience by allowing for custom model selection, API configuration for different backends, and real-time data processing through tool integration.

How to Use LLaMa-MCP-Streamlit

To start using LLaMa-MCP-Streamlit, you need to set up the environment and choose your preferred method of running the server. Here's a quick guide:

Configure Environment Variables: Ensure that your .env file is set up with the necessary API keys for NVIDIA and Ollama to enable seamless integration.
Running with Poetry:
- Install dependencies using Poetry:
```
poetry install
```
- Launch the Streamlit app:
```
poetry run streamlit run llama_mcp_streamlit/main.py
```
Running with Docker:
- Build the Docker image:
```
docker build -t llama-mcp-assistant .
```
- Run the Docker container:
```
docker compose up
```
Adjust MCP Server Configuration: Modify the utils/mcp_server.py file to select either NPX or Docker as your MCP server setup based on your needs.

Once set up, you can interact with the AI assistant through Streamlit's user-friendly chat interface, taking advantage of its real-time data retrieval and tool execution capabilities.

Key Features of LLaMa-MCP-Streamlit

Conversational Interface: Built with Streamlit, it offers a chat-based user experience that is intuitive and easy to use.
Custom Model Selection: Choose between NVIDIA NIM and Ollama models to fit your specific use case and requirements.
Real-time Tool Execution: Leverage the power of MCP to execute external tools and process data in real-time.
API Configuration: Customize the backend integration to suit various application needs.
Streamlined Deployment: Supports deployment via Docker for a containerized setup, making it easier to manage and scale.
Interactive UI Elements: Enjoy a visually appealing and interactive experience with Streamlit's UI components, designed for streamlined navigation and usage.

Whether you are looking to enhance productivity by integrating various tools or simply exploring the capabilities of a conversational AI assistant, LLaMa-MCP-Streamlit offers a comprehensive solution tailored to modern AI interaction needs.

This project is an interactive AI assistant built with Streamlit, NVIDIA NIM's API (LLaMa 3.3:70b)/Ollama, and Model Control Protocol (MCP). It provides a conversational interface where you can interact with an LLM to execute real-time external tools via MCP, retrieve data, and perform actions seamlessly. The assistant supports:

Custom model selection (NVIDIA NIM / Ollama)
API configuration for different backends
Tool integration via MCP to enhance usability and real-time data processing
A user-friendly chat-based experience with Streamlit

📸 Screenshots

Homepage Screenshot Tools Screenshot Chat Screenshot Chat (What can you do?) Screenshot

📁 Project Structure

llama_mcp_streamlit/
│── ui/
│ ├── sidebar.py # UI components for Streamlit sidebar
│ ├── chat_ui.py # Chat interface components
│── utils/
│ ├── agent.py # Handles interaction with LLM and tools
│ ├── mcp_client.py # MCP client for connecting to external tools
│ ├── mcp_server.py # Configuration for MCP server selection
│── config.py # Configuration settings
│── main.py # Entry point for the Streamlit app
.env # Environment variables
Dockerfile # Docker configuration
pyproject.toml # Poetry dependency management

🔧 Environment Variables

Before running the project, configure the .env file with your API keys:

# Endpoint for the NVIDIA Integrate API
API_ENDPOINT=
API_KEY=your_api_key_here
# Endpoint for the Ollama API
API_ENDPOINT=
API_KEY=ollama

🚀 Running the Project

Using Poetry

Install dependencies:

poetry install

Run the Streamlit app:

poetry run streamlit run llama_mcp_streamlit/main.py

Using Docker

Build the Docker image:

docker build -t llama-mcp-assistant .

Run the container:

docker compose up

🔄 Changing MCP Server Configuration

To modify which MCP server to use, update the utils/mcp_server.py file. You can use either NPX or Docker as the MCP server:

NPX Server

server_params = StdioServerParameters(
 command="npx",
 args=[
 "-y",
 "@modelcontextprotocol/server-filesystem",
 "/Users/username/Desktop",
 "/path/to/other/allowed/dir"
 env=None,

Docker Server

server_params = StdioServerParameters(
 command="docker",
 args=[
 "run",
 "-i",
 "--rm",
 "--mount", "type=bind,src=/Users/username/Desktop,dst=/projects/Desktop",
 "--mount", "type=bind,src=/path/to/other/allowed/dir,dst=/projects/other/allowed/dir,ro",
 "--mount", "type=bind,src=/path/to/file.txt,dst=/projects/path/to/file.txt",
 "mcp/filesystem",
 "/projects"
 env=None,

Modify the server_params configuration as needed to fit your setup.

📌 Features

Real-time tool execution via MCP
LLM-powered chat interface
Streamlit UI with interactive chat elements
Support for multiple LLM backends (NVIDIA NIM & Ollama)
Docker support for easy deployment

🛠 Dependencies

Python 3.11+
Streamlit
OpenAI API (for NVIDIA NIM integration)
MCP (Model Control Protocol)
Poetry (for dependency management)
Docker (optional, for containerized deployment)

📜 License

This project is licensed under the MIT License.

🤝 Contributing

Feel free to submit pull requests or report issues!

📬 Contact

For any questions, reach out via GitHub Issues.

How to Use

To use the LLaMa-MCP-Streamlit, follow these steps:

Visit https://github.com/Nikunj2003/LLaMa-MCP-Streamlithttps://github.com/Nikunj...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using LLaMa-MCP-Streamlit capabilities within your Claude conversations

Additional Information

Created

February 7, 2025

Company

Nikunj2003

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More