💰 Finance MCP Server

A personal finance tracker powered by the Model Context Protocol (MCP), allowing you to manage your income and expenses directly through Claude Desktop using natural language.

🚀 Features

• Add income and expense transactions

• Check your current balance

• List recent transactions

• Get a summary grouped by category

• Get a monthly summary (income, expenses, balance)

• Delete transactions by ID

• Persistent storage using SQLite

Related MCP server: Expense Tracker MCP Server

🛠️ Requirements

• Python 3.10+

• Claude Desktop

📦 Installation

1. Clone the repository:

git clone https://github.com/taylor3lewis/finance-mcp-server.git
cd finance-mcp-server

2. Create and activate a virtual environment:

python -m venv venv

# Windows
venv\Scripts\activate

# macOS/Linux
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

⚙️ Claude Desktop Configuration

Open your Claude Desktop config file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the following entry inside "mcpServers":

{
  "mcpServers": {
    "finance-mcp-server": {
      "command": "C:/path/to/your/venv/Scripts/python.exe",
      "args": ["C:/path/to/finance-mcp-server/server.py"]
    }
  }
}

⚠️ Replace the paths with the actual paths on your machine.

Restart Claude Desktop after saving the config file.

🧰 Available Tools

💬 Usage Examples

Once configured, just talk to Claude naturally:

"Mock 10 fake expenses in 3 different categories: food, leisure, and bills."

"What is my current balance?"

"Show me a summary of my expenses by category"

"If I maintain this monthly spending pattern, how much will I have spent by the end of the year?"

"How much did I spend in March 2026"

"List my last 5 transactions"

"delete entry with id = 2"

Using HTTP Client

Run MCP Server

python main.py http

Run Client in Another Shell

python client.py

🗂️ Project Structure

finance-mcp-server/
├── main.py            # MCP server with all tools
├── client.py          # MCP client to connect to server via API
├── requirements.txt   # Python dependencies
├── README.md          # Project documentation
└── data/
    └── finance.db     # SQLite database (auto-created on first run)