🚀 MarketIntel MCP Server

An AI-powered Market Research MCP (Model Context Protocol) Server built using FastMCP, Python, Tavily Search API, and Cursor AI. This project enables Large Language Models (LLMs) to access real-time market intelligence through reusable MCP tools, providing structured competitor analysis, pricing insights, product portfolio mapping, and company research.

---

📌 Project Overview

MarketIntel is a custom MCP server that exposes market research capabilities as reusable tools. It integrates with the Tavily Search API to retrieve live web data and allows AI assistants (such as Cursor AI) to generate structured market intelligence reports.

The project demonstrates how Model Context Protocol (MCP) enables AI applications to securely interact with external services while maintaining a standardized interface.

---

✨ Features

• 📊 Company Overview
• 🏢 Competitor Analysis
• 📦 Product Portfolio Mapping
• 💰 Pricing Intelligence
• 📰 Recent News Monitoring
• 📈 SWOT & Porter's Five Forces Prompt
• 🌐 Live Web Search using Tavily
• 🤖 Cursor AI MCP Integration
• ⚡ FastMCP Server using SSE Transport

---

Architecture

                    Cursor AI
                        │
                        │ MCP
                        ▼
              MarketIntel MCP Server
                        │
         ┌──────────────┼──────────────┐
         │              │              │
         ▼              ▼              ▼
 Company Overview   Competitor     Pricing
                     Analysis      Intelligence
         │              │              │
         └──────────────┼──────────────┘
                        ▼
                  Tavily Search API
                        │
                        ▼
                 Live Web Search Results

---

Tech Stack

• Python 3.12+
• FastMCP
• Tavily Search API
• Cursor AI
• uv Package Manager
• Server-Sent Events (SSE)

---

Project Structure

MarketIntel-MCP/
│
├── server.py
├── .env
├── pyproject.toml
├── uv.lock
├── README.md
└── .gitignore

---

MCP Tools

Company Overview

Returns:

• Company background
• Headquarters
• Products
• Business model
• Recent developments

---

Competitor Analysis

Returns:

• Major competitors
• Emerging competitors
• Regional competitors
• Market positioning

---

Product Portfolio

Maps:

• Products
• Solutions
• Pricing tiers
• Product categories

---

Pricing Snapshot

Retrieves:

• Pricing
• Billing models
• Discounts
• Regional pricing

---

Recent News Pulse

Returns latest news including:

• Product launches
• Acquisitions
• Funding
• Leadership changes

---

Prerequisites

Install:

• Python 3.12+
• Cursor AI
• uv
• Tavily API Account

---

Installation

Clone the repository

git clone https://github.com/<yourusername>/MarketIntel-MCP.git

cd MarketIntel-MCP

Install dependencies

uv sync

or

uv add fastmcp
uv add tavily-python
uv add python-dotenv

---

Configure Environment Variables

Create a .env file.

TAVILY_API_KEY=your_api_key_here

---

Run the MCP Server

uv run server.py

Expected output

🚀 Starting MarketIntel MCP Server...

FastMCP Server running on

http://127.0.0.1:8000/sse

---

Configure Cursor AI

Open

Settings
→ Tools & Integrations
→ Add Custom MCP

Use

{
  "mcpServers": {
    "MarketIntel": {
      "url": "http://127.0.0.1:8000/sse"
    }
  }
}

Restart Cursor AI.

---

Example Prompt

Create a market research report comparing NVIDIA and AMD.

Cover:

• Company Overview
• Product Portfolio
• Pricing
• Competitors
• Recent News
• Future Outlook

Keep the report under 300 words.

---

Example Workflow

User Prompt
      │
      ▼
Cursor AI
      │
      ▼
MarketIntel MCP Server
      │
      ▼
FastMCP Tool
      │
      ▼
Tavily Search API
      │
      ▼
Live Market Data
      │
      ▼
Structured AI Report

---

Skills Demonstrated

• Model Context Protocol (MCP)
• FastMCP Framework
• AI Tool Development
• Prompt Engineering
• REST API Integration
• AI Agent Development
• Market Research Automation
• Python Development
• Cursor AI Integration
• Server-Sent Events (SSE)

---

Future Enhancements

• OpenAI integration
• Azure AI Foundry integration
• Multi-agent orchestration
• Financial data connectors
• Vector database integration
• RAG-based document search
• Authentication & Authorization
• Docker support
• Kubernetes deployment
• CI/CD with GitHub Actions

---

Learning Outcomes

This project demonstrates how to:

• Build custom MCP servers
• Expose reusable AI tools
• Connect LLMs to external APIs
• Generate structured market intelligence
• Develop AI-powered business applications
• Integrate Cursor AI with MCP

---

References

• FastMCP Documentation
• Tavily API Documentation
• Cursor AI Documentation
• Model Context Protocol Specification

---

Author

Arun Kumar

Principal Data & AI Architect

Specializing in:

• AI Agents
• Azure AI
• Data Engineering
• Cloud Architecture
• Generative AI
• Enterprise AI Solutions

---

License

This project is intended for educational and learning purposes.