LunchMoney

v1.4.1Finance & Fintechstable

An MCP server implementation that provides programmatic access to personal finance data through LunchMoney's API, enabling AI assistants to manage transactions, budgets, categories, and assets.

dxtlunchmoneylunchmoney-apimcpmcp-server
Share:
70
Stars
0
Downloads
0
Weekly
0/5

What is LunchMoney?

LunchMoney is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server implementation that provides programmatic access to personal finance data through lunchmoney's api, enabling ai assistants to manage transactions, budgets, categories, and assets.

An MCP server implementation that provides programmatic access to personal finance data through LunchMoney's API, enabling AI assistants to manage transactions, budgets, categories, and assets.

This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP server implementation that provides programmatic acce

Use Cases

Query personal finance data and transaction history.
Manage budgets and categories programmatically.
Track assets and spending through AI integration.
akutishevsky

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.4.1
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @akutishevsky/lunchmoney-mcp

Manual Installation

npx -y @akutishevsky/lunchmoney-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LunchMoney

The LunchMoney MCP server connects AI assistants to LunchMoney, a personal finance and budgeting app, via its developer API. It enables natural language management of transactions, budgets, categories, tags, recurring expenses, Plaid-connected bank accounts, cryptocurrency holdings, and more — covering the full LunchMoney data model. Finance-conscious developers and power users of LunchMoney can use it to query spending history, automate transaction categorization, split expenses, and analyze budgets through conversational AI without manually navigating the LunchMoney web interface.

Prerequisites

  • A LunchMoney account at lunchmoney.app
  • A LunchMoney API token from Settings > Developers in your LunchMoney dashboard
  • Node.js 16+ and npm (for npx-based installation)
  • An MCP-compatible client: Claude Desktop, Claude Code, Cursor, or VS Code
1

Get your LunchMoney API token

Log into LunchMoney, navigate to Settings > Developers, and generate a personal access token. Copy the token — you will need it for every configuration method.

2

Install via Claude Code CLI (recommended)

If using Claude Code, add the LunchMoney MCP server in a single command. This handles configuration automatically.

claude mcp add lunchmoney --transport stdio \
  -e LUNCHMONEY_API_TOKEN=your-api-token-here \
  -- npx -y @akutishevsky/lunchmoney-mcp
3

Or configure Claude Desktop manually

Add the LunchMoney server to your Claude Desktop configuration file. The optional LUNCHMONEY_DEBUG variable enables verbose API logging for troubleshooting.

{
  "mcpServers": {
    "lunchmoney": {
      "command": "npx",
      "args": ["-y", "@akutishevsky/lunchmoney-mcp"],
      "env": {
        "LUNCHMONEY_API_TOKEN": "your-api-token-here",
        "LUNCHMONEY_DEBUG": "false"
      }
    }
  }
}
4

Restart your MCP client

Fully quit and relaunch Claude Desktop or your MCP client after saving the configuration. The LunchMoney tools should appear in the available tools list.

5

Test the connection with a simple query

Ask Claude to retrieve your current month's budget summary or list recent transactions to verify the API token and connection are working correctly.

LunchMoney Examples

Client configuration

Claude Desktop JSON configuration for the LunchMoney MCP server using the official npm package.

{
  "mcpServers": {
    "lunchmoney": {
      "command": "npx",
      "args": ["-y", "@akutishevsky/lunchmoney-mcp"],
      "env": {
        "LUNCHMONEY_API_TOKEN": "your-api-token-here",
        "LUNCHMONEY_DEBUG": "false"
      }
    }
  }
}

Prompts to try

Conversational queries you can use with Claude to manage your LunchMoney data.

- "Show me my budget summary for this month, broken down by category"
- "List all transactions over $100 from the past two weeks"
- "Create a new expense for $45.99 at Amazon in the Shopping category for today"
- "List all my recurring expenses and their next due dates"
- "Split the $120 dinner transaction equally between Food and Entertainment categories"

Troubleshooting LunchMoney

API token authentication fails with 401 Unauthorized

Regenerate your token in LunchMoney under Settings > Developers. Ensure the token is pasted without leading or trailing whitespace in the LUNCHMONEY_API_TOKEN environment variable.

Missing fields or unexpected errors after upgrading to v2.0.0

Version 2.0.0 introduced breaking API changes: asset fields were renamed to `manual_account_id`, tag arrays changed to `tag_ids`, and budget endpoints were restructured. If you use custom prompts referencing old field names, update them to match the new schema.

Debug mode produces too much output

Set `LUNCHMONEY_DEBUG` to `false` or remove it from the env block entirely. Debug mode is only useful when diagnosing API request/response issues — leave it disabled for everyday use.

Frequently Asked Questions about LunchMoney

What is LunchMoney?

LunchMoney is a Model Context Protocol (MCP) server that mcp server implementation that provides programmatic access to personal finance data through lunchmoney's api, enabling ai assistants to manage transactions, budgets, categories, and assets. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LunchMoney?

Install via npm with the command: npx -y @akutishevsky/lunchmoney-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with LunchMoney?

LunchMoney works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LunchMoney free to use?

Yes, LunchMoney is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Finance & Fintech MCP Servers

Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "lunchmoney-mcp-server": { "command": "npx", "args": ["-y", "@akutishevsky/lunchmoney-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LunchMoney?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides