MCP.so
ログイン

MCP Hub Project

@CodeHalwell

リポジトリ

MCP Hub Project について

Repo to hold the code for the mcp server built in Gradio for the agents and mcp hackathon

#gradio#mcp#research-assistant

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

CodeHalwell

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": {
    "gradio-mcp-agent-hack": {
      "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 Hub Project?

MCP Hub Project is a sophisticated research assistant built using Gradio’s MCP server functionality, orchestrating a 5-step deep research workflow. It demonstrates how to build interconnected AI agents that work together to provide deep research capabilities.

How to use MCP Hub Project?

Install Python 3.12+, set up a virtual environment, install dependencies with pip install -r requirements.txt, create a .env file with your Nebius and Tavily API keys, then run python main.py to launch the Gradio interface at http://127.0.0.1:7860/. The MCP schema is available at /gradio_api/mcp/schema.

Key features of MCP Hub Project

  • 5-step deep research workflow (enhancement, search, summarization, citation, combination)
  • Multi-agent architecture for interconnected agent services
  • Real-time web search via Tavily API
  • LLM processing using Nebius (OpenAI-compatible) models
  • Automatic APA-style citation generation from web sources
  • MCP server implementation built on Gradio

Use cases of MCP Hub Project

  • Automated research assistant that breaks down complex queries into structured sub‑questions
  • Generating comprehensive, citation‑aware summaries from multiple web searches
  • Learning how to build MCP‑compatible multi‑agent workflows with Gradio
  • Integrating real‑time search and LLM summarization in a single pipeline

FAQ from MCP Hub Project

What APIs does MCP Hub Project require?

It requires API keys for Nebius and Tavily. Both must be set in a .env file.

What Python version is needed?

Python 3.12+ is required.

How do I start the MCP server?

Run python main.py. The Gradio app launches at http://127.0.0.1:7860/ and the MCP schema is available at /gradio_api/mcp/schema.

What agents are included?

Five agents: Question Enhancer, Web Search Agent, LLM Processor, Citation Formatter, and an Orchestrator that coordinates the workflow.

Where can I find tutorial examples?

The tutorial_scripts/ directory contains example Gradio applications such as simple_app.py and letter_count.py for learning MCP features.

コメント

「AI とエージェント」の他のコンテンツ

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

meGPT - upload an author's content into an LLM

adrianco

Code to process many kinds of content by an author into an MCP server

287

Unreal Engine Generative AI Support Plugin

prajwalshettydev

Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti

622

MCP Manager for Claude Desktop

zueai

simple web ui to manage mcp (model context protocol) servers in the claude app

290

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