How do I use MCP AI Research Assistant?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP AI Research Assistant summarize the article on renewable energy breakthroughs" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP AI Research Assistant by paneri11

MCP AI Research Assistant (Offline)

📌 Overview

An offline AI Research Assistant built using the Model Context Protocol (MCP). The system uses a FastMCP server exposing structured tools and a custom client orchestrator communicating via stdio transport.

This project demonstrates end-to-end MCP integration without external APIs.

🚀 Features:

Summarize research text Extract key points Save research notes locally Retrieve saved notes Fully offline stdio-based MCP transport Structured tool invocation

🏗 Architecture

  User CLI

      ↓

  MCP Client

      ↓ (stdio transport)

  FastMCP Server

      ↓

  Tool Execution Layer

      ↓

  notes.json

🛠 Tech Stack:

Python 3.13

Model Context Protocol (MCP) v1.26.0

FastMCP

AsyncIO

▶️ How To Run:

Clone repository: git clone https://github.com/paneri11/mcp-ai-research-assistant.git
cd mcp-ai-research-assistant
Create virtual environment: python -m venv venv
venv\Scripts\activate # Windows
Install dependencies: pip install -r requirements.txt
Run: python client/client.py