README.md

metadata

title: MCP Research
emoji: 🚀
colorFrom: red
colorTo: red
sdk: docker
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: Streamlit template space

AI-Powered Scientific Research Companion

This repository implements an AI-driven research assistant using the Model Context Protocol (MCP). It enables end-to-end capabilities:

• 🔍 Discovery & Ingestion: Search journals, preprint servers, and web via MCP servers (e.g. pskill9/web-search, metatool-ai/metatool-app).
• 📓 Reproducible Notebook: Retrieve and run code snippets for core experiments via a Python-run MCP server.
• 🔗 Knowledge Graph: Build and visualize relationships (methods, datasets, concepts) via a vector-store MCP (e.g. Chroma).
• 🔧 Provenance Tracking: Store metadata and run history in a SQL database via MCP.

Getting Started

1. Clone this repo:

   git clone https://huggingface.co/spaces/your-username/MCP_Research
   cd MCP_Research