MCP.so
ログイン

💬 MCP Assistant Playground

@niawjunior

リポジトリ

💬 MCP Assistant Playground について

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.

#gpt-4o#mcp-server#mcp-client

基本情報

カテゴリ

AI とエージェント

ランタイム

python

トランスポート

stdio

公開者

niawjunior

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-assistant-playground": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is 💬 MCP Assistant Playground?

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.

How to use 💬 MCP Assistant Playground?

Clone the repository, set up a Python 3.10+ virtual environment, install dependencies from requirements.txt, create a .env file with OPENAI_API_KEY (and optionally SUPABASE_URL and SUPABASE_KEY), then run python launch.py and access the chat interface at http://localhost:8501.

Key features of 💬 MCP Assistant Playground

  • Natural language tool selection using GPT-4o
  • MCP tool execution via fastmcp
  • Real-time image generation with DALL·E 3
  • Text-to-speech synthesis (GPT-4o mini TTS)
  • Supabase integration for member CRUD operations
  • Streamlit UI with image and audio rendering

Use cases of 💬 MCP Assistant Playground

  • Chat with GPT and generate images on the fly
  • Query and manage Supabase database members via natural language
  • Create text-to-speech audio from conversational prompts
  • Experiment with AI-driven tool routing and confirmation flows

FAQ from 💬 MCP Assistant Playground

What are the prerequisites?

Python 3.10+ is required. You need an OpenAI API key; a Supabase project is optional for member tool features.

How do I start the application?

Clone the repository, set up a virtual environment, install dependencies, create a .env file with your keys, and run python launch.py. Then

コメント

「AI とエージェント」の他のコンテンツ

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K