About 💬 MCP Assistant Playground
MCP Assistant Playground is a Streamlit chat interface using OpenAI GPT-4o, for experimenting with natural-language tool routing. It runs custom tools through fastmcp and renders image and audio results.
Key features
- 01GPT-4o natural-language tool selection
- 02MCP tool execution via fastmcp
- 03OpenAI image generation
- 04Text-to-speech synthesis
- 05Supabase member CRUD
- 06Streamlit tool-result rendering
Use cases
- 01Select tools from natural-language requests
- 02Generate and view image results
- 03Convert text to speech
- 04Manage Supabase member records
MCP support
The project executes MCP tools through fastmcp, using capabilities such as GPT chat, image generation, Supabase queries, and text-to-speech in its chat interface.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README💬 MCP Assistant Playground
https://github.com/user-attachments/assets/c60a59c0-5ff5-487e-be47-bdcc8253fbc8
https://github.com/user-attachments/assets/85e7453f-950d-41a4-a1f5-1abd3a587067
A Streamlit-based chatbot interface powered by OpenAI GPT-4o that intelligently routes user input to custom MCP tools such as GPT chat, image generation, Supabase queries, and text-to-speech.
Built for rapid experimentation with AI-powered tool routing, inspired by Claude-style confirmation flows.
✨ Features
- Natural language tool selection using GPT-4o
- MCP tool execution via
fastmcp - Real-time OpenAI image generation (DALL·E 3)
- Text-to-speech audio synthesis (GPT-4o mini TTS)
- Supabase integration for member CRUD operations
- Streamlit UI with tool result rendering (image/audio)
🛠️ Prerequisites
- Python 3.10+
- OpenAI API key
- Supabase project (optional, for member tools)
🧪 Getting Started
1. Clone the repository
git clone https://github.com/niawjunior/mcp-assistant-playground.git
cd mcp-assistant-playground
2. Set up virtual environment
python -m venv .venv
source .venv/bin/activate # or `.venv\Scripts\activate` on Windows
3. Install dependencies
pip install -r requirements.txt
4. Set up environment variables
Create a .env file in the root directory with the following variables:
OPENAI_API_KEY=your_openai_api_key
SUPABASE_URL=your_supabase_url
SUPABASE_KEY=your_supabase_key
5. Run the application
python launch.py
6. Access the chat interface
Open your web browser and navigate to http://localhost:8501.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.