MCP Hub Project
@CodeHalwell
Repo to hold the code for the mcp server built in Gradio for the agents and mcp hackathon
Overview
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.
