LLaMa-MCP-Streamlit

Name: LLaMa-MCP-Streamlit
Rating: 1.8 (43 reviews)
Author: Nikunj2003

by Nikunj2003·★ 43·Score 36

A Streamlit AI assistant using MCP to enable tool interactions with LLaMa 3.3 or Ollama models.

ai-llmdeveloper-toolsproductivity

Forks

Open issues

15 mo ago

Last commit

2d ago

Indexed

Overview

This project creates a conversational AI interface that leverages Model Control Protocol (MCP) to enable real-time external tool execution. It provides a user-friendly chat experience using Streamlit, with support for both NVIDIA NIM API (LLaMa 3.3:70b) and Ollama backends. The architecture includes MCP client functionality to connect to various external tools and services. The project is well-structured with clear separation of UI components, agent logic, and MCP configuration.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Creating an interactive chat interface that can execute commands via MCP

you:Building a custom AI assistant with access to file system tools

you:Developing a prototype for LLM applications with external tool integration

you:What MCP servers are supported?

you:Can I use this with other LLM providers?

When to choose this

Choose this when you need a quick prototype for an MCP-integrated AI assistant with a UI, especially if you're already using Streamlit or Docker.

When NOT to choose this

Don't choose this for production deployment due to limited documentation and the project appears to be a prototype rather than a fully-fledged application.

Comparable tools

streamlit-mcpmcp-streamlit-examplesnvidia-mcp-serverollama-mcp

Installation

Installation Steps

Clone the repository
Set up environment variables in .env file:

```bash # NVIDIA NIM API API_ENDPOINT=https://integrate.api.nvidia.com/v1 API_KEY=your_api_key_here

# Ollama API_ENDPOINT=http://localhost:11434/v1/ API_KEY=ollama ```

Install dependencies using Poetry:

``bash poetry install ``

Run the Streamlit app:

``bash poetry run streamlit run llama_mcp_streamlit/main.py ``

To use with Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "llama-mcp-streamlit": {
      "command": "python",
      "args": ["path/to/llama_mcp_streamlit/utils/mcp_server.py"]
    }
  }
}

FAQ

What MCP servers are supported?: The project supports MCP servers that can be run via NPX or Docker, including the filesystem server (@modelcontextprotocol/server-filesystem). Configuration is modified in the utils/mcp_server.py file.
Can I use this with other LLM providers?: The project currently supports NVIDIA NIM (LLaMa 3.3:70B) and Ollama. Additional providers would require modifying the API configuration in the agent.py file.

Compare LLaMa-MCP-Streamlit with

LLaMa-MCP-Streamlit vs ultimate_mcp_server LLaMa-MCP-Streamlit vs mcp-server-chart LLaMa-MCP-Streamlit vs everything LLaMa-MCP-Streamlit vs filesystem LLaMa-MCP-Streamlit vs time

GitHub →

Last updated 2026-05-17 · Auto-generated from public README + GitHub signals.