lunchmoney-mcp

lunchmoney-mcp

An MCP server that lets AI assistants interact with your Lunchmoney data, enabling natural language queries about transactions, budgets, and spending patterns.

leafeye

Finance
Visit Server

Tools

get-budget-summary

Get budget summary for a specific time period

get-recent-transactions

Get recent transactions

search-transactions

Search transactions by keyword

get-category-spending

Get spending in a category

README

Lunchmoney MCP Server

A Model Context Protocol (MCP) server that lets you interact with your Lunchmoney transactions and budgets through Claude and other AI assistants.

What is this?

This tool allows you to connect your Lunchmoney financial data to Claude AI, so you can ask questions about your spending, analyze your budget, and get insights about your finances through a natural conversation.

Features

This server provides four main tools:

  1. get-recent-transactions: View your recent transactions from the past N days
  2. search-transactions: Search transactions by keyword in payee names or notes
  3. get-category-spending: Analyze spending in specific categories
  4. get-budget-summary: Get detailed budget information including spending, remaining amounts, and recurring items

Privacy and Data Handling

Important: MCP provides a structured way for Claude to interact with your Lunchmoney data while maintaining privacy boundaries. Here's what you should know:

  • Claude (the host) creates a client that connects to your local MCP server
  • Your Lunchmoney API token stays on your local machine
  • The MCP server runs locally and fetches data from Lunchmoney's API
  • You will be asked to approve each request to access your Lunchmoney data
  • When you ask a question about your finances, Claude requests specific information from the MCP server
  • The MCP server processes your request locally and returns only the relevant results
  • Claude never has direct access to your full financial data or API token
  • Only the specific information requested (like transaction summaries or budget status) is shared with Claude
  • Anthropic's data retention policies apply to these summary results that are part of your conversation
  • Each server connection is isolated, maintaining clear security boundaries

You can find more about MCP in the documentaion: https://modelcontextprotocol.io/introduction

Installation

Also look at the offical Claude documentation: https://modelcontextprotocol.io/quickstart/user

Using npx

Node.js is a software platform that lets you run JavaScript code on your computer (outside of a web browser).

To install Node.js:

  • Windows/Mac: Download and run the installer from the official Node.js website
  • Mac with Homebrew: Run brew install node in Terminal
  • Linux: Use your package manager (e.g., sudo apt install nodejs for Ubuntu)

Once Node.js is installed on your computer, you can run the server directly without downloading anything:

  1. Get your Lunchmoney API token from your Lunchmoney developer settings
  2. Open Claude Desktop
  3. Go to Settings → Developer -> Edit Config
  4. Add the following configuration:
{
  "mcpServers": {
    "lunchmoney": {
      "command": "npx",
      "args": ["-y", "lunchmoney-mcp-server"],
      "env": {
        "LUNCHMONEY_TOKEN": "your_token_here"
      }
    }
  }
}

Replace your_token_here with your actual Lunchmoney API token.

Important Note: After changing the configuration, you may need to restart Claude Desktop for the changes to take effect.

Example Usage

Once configured in Claude Desktop, you can ask questions like:

Transactions

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

Budgets

  • "Show me my budget summary for this month"
  • "What's my budget status from January to March 2024?"
  • "How much of my food budget is remaining?"
  • "Show me categories where I'm over budget"

What is MCP?

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). Think of MCP like a USB-C port for AI applications - it provides a standardized way to connect AI models to different data sources and tools.

Some key benefits of MCP:

  • Standardized way to expose data and functionality to LLMs
  • Human-in-the-loop security (all actions require user approval)
  • Growing ecosystem of pre-built integrations
  • Works with multiple AI models and applications

Troubleshooting

Claude says it can't connect to my MCP server:

  • Make sure the configuration in Claude's Developer settings is correct
  • Try restarting Claude Desktop after changing the configuration
  • Check that your Lunchmoney API token is valid

Claude doesn't recognize Lunchmoney commands:

  • Start a new conversation in Claude
  • Try explicitly mentioning Lunchmoney in your query (e.g., "Show me my recent Lunchmoney transactions")

API Notes

  • Budget data must use month boundaries for dates (e.g., 2024-01-01 to 2024-01-31)
  • Transactions can use any date range
  • All monetary values are returned in their original currency

License

MIT

Contributing

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

Recommended Servers

Crypto Price & Market Analysis MCP Server

Crypto Price & Market Analysis MCP Server

A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.

Featured
TypeScript
chromia-mcp

chromia-mcp

Enables AI to interact with Chromia Wallet for sending $CHR transactions.

Official
Local
TypeScript
TripleWhale MCP Server

TripleWhale MCP Server

An implementation of Model Context Protocol (MCP) that allows users to interact with TripleWhale's e-commerce analytics platform using natural language queries through Claude Desktop.

Official
Local
TypeScript
Adamik MCP Server

Adamik MCP Server

Enables read and write interactions with 60+ blockchain networks through Claude Desktop, providing a standardized multi-chain API for transaction management, account insights, staking, and token interactions.

Official
Local
TypeScript
Open-Ledger-MCP-Server

Open-Ledger-MCP-Server

A Model Context Protocol (MCP) server implementation for the OpenLedger API. This server provides structured context to AI models according to the MCP specification.

Official
TypeScript
ntropy-mcp MCP Server

ntropy-mcp MCP Server

Enables enriching banking data with the Ntropy API, providing tools to create account holders and enrich transactions efficiently.

Official
Python
Iaptic MCP Server

Iaptic MCP Server

A server for interacting with the Iaptic API, allowing AI models like Claude to query customer, purchase, and transaction data, as well as retrieve statistical insights.

Official
TypeScript
Bitrefill Search and Shop

Bitrefill Search and Shop

This MCP wraps Bitrefill public API to allow agents to search for products and shop using cryptocurrencies like Bitcoin, Ethereum, Solana, and many more.

Official
TypeScript
MCP EVM Signer

MCP EVM Signer

A server that securely manages Ethereum private keys locally and enables Claude for Desktop to interact with EVM-compatible blockchains through Infura.

Local
TypeScript
Cryptocurrency Daemon MCP Server

Cryptocurrency Daemon MCP Server

Enables secure interactions with cryptocurrency daemon RPC interfaces through AI assistants, supporting transaction management, wallet operations, and daemon monitoring for Bitcoin-derived cryptocurrencies.

Local
TypeScript