MarketIntel MCP Server

A minimal MCP server for market research built with FastMCP and the Tavily API with n8n automation.

Overview

This repository includes:

• server.py — MCP server implementation using FastMCP

• client.py — example client that compares two companies using the MCP server

• main.py — placeholder entrypoint

• MCP-Market-Research Agent.json — optional integration configuration

• requirements.txt / pyproject.toml — Python dependencies

Related MCP server: tavily-fastmcp

Steps

1. Clone or download this repository.

2. Create a Python virtual environment in the repository root:

python -m venv .venv
source .venv/bin/activate

3. Install the dependencies:

pip install -r requirements.txt

4. Copy env-example file to a .env file in the repository root with your Tavily API key:

TAVILY_API_KEY=your_api_key_here
N8N_API_KEY=your_api_key_here

5. Start the MCP server:

python server.py

6. In a separate terminal, run the example client to compare two companies:

python client.py "openai vs anthropic"

7. To use a custom server endpoint, set MARKETINTEL_ENDPOINT and rerun the client:

MARKETINTEL_ENDPOINT=http://127.0.0.1:8000/mcp python client.py "openai vs anthropic"

Prerequisites

• Python 3.13+

• A valid Tavily API key

Setup

1. Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate

2. Install dependencies:

pip install -r requirements.txt

3. Create a .env file containing:

TAVILY_API_KEY=your_api_key_here

Running the server

Start the server with:

python server.py

The server listens on http://0.0.0.0:8000 and exposes the MCP endpoint at http://127.0.0.1:8000/mcp.

Using the client

Run the example client to compare two companies:

python client.py "openai vs anthropic"

To override the endpoint:

MARKETINTEL_ENDPOINT=http://127.0.0.1:8000/mcp python client.py "simplilearn vs edureka"

Project structure

.env                        # local environment variables
README.md                   # project documentation
server.py                   # MCP server implementation
client.py                   # example FastMCP client
main.py                     # placeholder entrypoint
MCP-Market-Research Agent.json  # optional integration config
pyproject.toml              # project metadata
requirements.txt            # dependency list
python-version              # pinned Python version
uv.lock                     # dependency lockfile
.venv/                      # virtual environment (ignored)

Server capabilities

The server exposes the following tools:

• company_overview

• list_competitors

• product_portfolio

• pricing_snapshot

• recent_news_pulse

It also defines a market topics resource and a competitor analysis prompt.

Environment variables

• TAVILY_API_KEY — required for Tavily access

• MARKETINTEL_ENDPOINT — optional client override

Notes

• This repository does not include an mcp_server/ package or tests/ directory.

• The current implementation is centered on the server.py and client.py examples.

Development

To install optional dev tooling:

pip install flake8
flake8 .