lunchmoney
A Model Context Protocol (MCP) server implementation for LunchMoney, providing programmatic access to personal finance management through LunchMoney's API.
claude mcp add --transport stdio akutishevsky-lunchmoney-mcp npx @akutishevsky/lunchmoney-mcp \ --env LUNCHMONEY_DEBUG="true" \ --env LUNCHMONEY_API_TOKEN="your-api-token-here"
How to use
LunchMoney MCP Server provides programmatic access to your LunchMoney data via the MCP protocol. It exposes a suite of tools for managing users, categories, tags, transactions, budgets, assets, Plaid accounts, and cryptocurrency holdings by interfacing with LunchMoney's API. The server uses a token-efficient encoding (TOON) for responses to optimize prompts in AI workflows, and is designed to plug into MCP-compatible clients like Claude Desktop. To use it, configure an MCP client to point at the LunchMoney server entry (usually by specifying the npx-based launch command and your LunchMoney API token). When you start the server, supply your LunchMoney API token and, optionally, enable debug logging to stderr for troubleshooting. The available tools allow you to retrieve data, create or modify records, and perform common financial management tasks through natural-language prompts processed by the MCP client.
How to install
Prerequisites:
- Node.js 16+ installed and available in your PATH
- npm or npx available
- A LunchMoney API token with appropriate permissions
Install and run the MCP server locally:
- Install the MCP using npx (no global install required):
LUNCHMONEY_API_TOKEN=your-api-token npx @akutishevsky/lunchmoney-mcp
- Alternatively, if you want to pin a specific version, you can run:
LUNCHMONEY_API_TOKEN=your-api-token npx @akutishevsky/lunchmoney-mcp@latest
- If you need to configure via MCP client configuration, use the following example to add LunchMoney as an MCP server:
{
"mcpServers": {
"lunchmoney": {
"command": "npx",
"args": ["@akutishevsky/lunchmoney-mcp"],
"env": {
"LUNCHMONEY_API_TOKEN": "your-api-token-here",
"LUNCHMONEY_DEBUG": "true"
}
}
}
}
- Start the server and point your MCP client to the LunchMoney server entry (name: lunchmoney). Ensure your API token remains private and is not shared publicly.
Additional notes
Tips and common issues:
- Ensure your LunchMoney API token has the necessary permissions for the actions you intend to perform.
- If you encounter rate limits or API errors, enable LUNCHMONEY_DEBUG to get verbose request/response logs for troubleshooting.
- The server is designed to work as an MCP Bundle or via a client’s JSON configuration; for Claude Desktop, you can install the bundle or add it to the configuration under mcpServers.
- If the token or environment variables are not picked up, verify your shell exports and restart the MCP client or process.
- For production deployments, consider using a dedicated environment file or secret manager to inject LUNCHMONEY_API_TOKEN securely.
Related MCP Servers
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
Matryoshka
MCP server for token-efficient large document analysis via the use of REPL state
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
Agentic -Skill
Agentic-MCP, Progressive MCP client with three-layer lazy loading. Validates AgentSkills.io pattern for efficient token usage. Use MCP without pre-install & wasting full-loading
mongo
MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB
vscode-context
MCP Server to Connect with VS Code IDE