Leafeye Lunchmoney MCP Server

🚀 Lunchmoney MCP Server

A Model Context Protocol (MCP) server that enables you to interact with Lunchmoney's transactions and budgets via Claude and other AI assistants.

🚀 Quick Start

The Lunchmoney MCP Server allows seamless interaction with Lunchmoney's transactions and budgets through AI assistants. After installation, you can start querying transaction and budget information right away.

✨ Features

This server offers four main tools:

1. View Recent Transactions: Check recent transactions within the past N days.
2. Search Transactions: Search for transactions by the payer's name or keywords in the notes.
3. Analyze Categorical Spending: View spending in specific categories.
4. Get Budget Overview: Obtain detailed budget information, including spending, remaining amounts, and recurring items.

📦 Installation

Install via Smithery

To automatically install the Lunchmoney MCP Server to the Claude desktop via Smithery:

npx -y @smithery/cli install @leafeye/lunchmoney-mcp-server --client claude

You can use this server directly on the Claude desktop without installation:

{
  "mcpServers": {
    "lunchmoney": {
      "command": "npx",
      "args": ["-y", "lunchmoney-mcp-server"],
      "env": {
        "LUNCHMONEY_TOKEN": "your_token_here"
      }
    }
  }
}

Replace your_token_here with your Lunchmoney API token, which you can obtain in your Lunchmoney developer settings.

💻 Usage Examples

Basic Usage

After configuring on the Claude desktop, you can ask the following questions:

Transactions

• "Show me my recent transactions from the past week."
• "Search for all Amazon transactions."
• "How much did I spend at restaurants last month?"
• "Find transactions marked as business expenses."

Budgets

• "Show me the budget overview for this month."
• "What was the budget status from January to March 2024?"
• "How much is left in my food budget?"
• "Show categories that are over budget."

📚 Documentation

What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs). Think of it as the USB - C port for AI applications—it offers a standardized way to connect different data sources and tools to AI models.

Some key advantages of MCP:

• A standardized way to expose data and functionality to large language models.
• Security for human - AI collaboration (all operations require user approval).
• A growing ecosystem of off - the - shelf integrations.
• Support for multiple AI models and applications.

🔧 Technical Details

Development

To develop locally:

1. Clone this repository.
2. Install dependencies:

npm install

3. Build the TypeScript code:

npm run build

4. Run with the API token:

LUNCHMONEY_TOKEN=your_token_here node build/index.js

5. Test with the MCP Inspector:

LUNCHMONEY_TOKEN=your_token_here npx @modelcontextprotocol/inspector node build/index.js

API Notes

• Budget data must use month - boundary dates (e.g., 2024 - 01 - 01 to 2024 - 01 - 31).
• Transactions can use any date range.
• All currency values are returned in the original currency.
• Category names are case - insensitive when searching.

📄 License

MIT

Contribution

Contributions are welcome! Please feel free to submit a Pull Request.