MCP Catalogs
Homemcp-playground screenshot

mcp-playground

by Elkhn·45·Score 45

A Streamlit-based chat playground with plug-and-play MCP server support for various LLM providers.

ai-llmdeveloper-toolsproductivity
17
Forks
0
Open issues
2 mo ago
Last commit
2d ago
Indexed

Overview

MCP Playground is a comprehensive chat application that combines Streamlit UI with MCP protocol support for external tool integration. It demonstrates a production-ready architecture using Docker Compose to orchestrate multiple services, including MCP servers for weather and currency data. The application is provider-agnostic, supporting OpenAI, Amazon Bedrock, Anthropic, Google Gemini, and Groq through LangChain and LangGraph implementations.

Try asking AI

After installing, here are 3 things you can ask your AI assistant:

you:Creating a custom AI agent playground with specialized tools
you:Developing and testing MCP servers with a real client interface
you:Demonstrating multi-model LLM integration with external APIs

When to choose this

Choose this playground when you need to quickly prototype and test MCP tool integrations across multiple LLM providers with minimal setup.

When NOT to choose this

Don't choose this for production deployments as it's designed for development/testing purposes and lacks robust authentication mechanisms.

Tools this server exposes

4 tools extracted from the README
  • get_current_weatherasync def get_current_weather(location: str) -> dict

    Get current weather information for a specific location

  • get_forecastasync def get_forecast(location: str, days: int = 3) -> dict

    Get weather forecast for a specified location and number of days

  • get_currency_ratesasync def get_currency_rates(date: str = None) -> dict

    Get current currency exchange rates

  • convert_currencyasync def convert_currency(amount: float, from_currency: str, to_currency: str, date: str = None) -> dict

    Convert an amount from one currency to another

Comparable tools

langchain-playgroundmcp-server-starterfastmcpstreamlit-chat

Installation

Installation

Prerequisites:

  • Docker ≥ 24
  • Docker Compose
  • At least one LLM provider API key

Quick Start:

git clone https://github.com/Elkhn/mcp-playground.git
cd mcp-playground
docker compose up --build

Access the application at http://localhost:8501

To integrate with Claude Desktop, add to your claude_desktop_config.json:

{
  "mcpServers": {
    "weather": {
      "command": "docker",
      "args": ["run", "--rm", "-p", "8000:8000", "weather-server"]
    }
  }
}

Compare mcp-playground with

GitHub →

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