Simple MCP with Tavily + Cherry Studio

A minimal implementation of MCP (Model Context Protocol) using:

• Tavily for web search.
• Cherry Studio as the MCP client.
• API Key (OpenAI, Groq, Gemini, etc)

---

Requirements

• Python 3.11
• uv

---

Features

• Tavily-powered web search tool.
• Fully compatible with Cherry Studio via MCP.

---

Getting Started

1. Clone the Repository

git clone https://github.com/your-username/simple-mcp.git
cd simple-mcp

2. Install uv

curl -Ls https://astral.sh/uv/install.sh | bash

Make sure ~/.local/bin is in your PATH:

export PATH="$HOME/.local/bin:$PATH"

3. Setup Environment

uv venv
source .venv/bin/activate
uv pip install -e .

---

Cherry Studio Setup (MCP Integration)

1. Open Cherry Studio
2. Go to Settings → MCP Servers → Add Server
3. Configure as follows:

• Name: simple-mpc
• Description: first project
• Type: STDIO
• Command:

  /home/your-username/.local/bin/uv   # <- path UV
  

• Arguments:

  --directory
  /home/your-username/Projects/simple-mcp
  run
  get_stock_price.py
  

• Environment Variables:

  TAVILY_API_KEY=your-tavily-api-key
  TAVILY_API_URL=https://api.tavily.com/search
  

4. Click Save
5. Activate the MCP toggle

Note: Replace /home/your-username/... with your actual project path.

Example configuration:

---

Download Cherry Studio

• Windows: Download EXE
• macOS: Download DMG
• Linux: Download AppImage

For Linux Users

chmod +x Cherry-Studio-1.1.17-x86_64.AppImage
./Cherry-Studio-1.1.17-x86_64.AppImage

please follow the tutorial below, you only need to change the name of the application with Cherry-Studio...AppImage

• Cursor AI: From Installation to Mastery on Linux 2025 (Tutorial)

  Note: Download image cherry.png (search on google) and move using following cmd

  sudo mv cherry.png /opt/cherry.png

---

Available Tool

• get_articles
• get_stock_price
• get_stock_price_history
• compare_stocks

---

Resources

• Tavily API Docs
• Cherry Studio Docs
• MCP Setup Guide

---