Money Lover MCP Server
Enables AI assistants to interact with Money Lover personal finance app through unofficial REST API. Supports authentication, wallet management, transaction querying, and creating new transactions for expense tracking.
README
Money Lover MCP Server
Node.js implementation of a Model Context Protocol (MCP) server that wraps the unofficial Money Lover REST API. The server exposes authentication and wallet management capabilities as MCP tools, enabling AI assistants or compatible MCP clients to login, inspect wallets, query transactions, and create new transactions.
Features
- Login tool returns Money Lover JWT tokens via the public OAuth flow.
- Tools for retrieving user info, wallets, categories, and transactions.
- Tool for adding new transactions, mirroring the behaviour of the Go reference client.
- Stdio-based server entrypoint that can be consumed by MCP-aware clients.
- Node-friendly REST wrapper for direct programmatic usage.
Prerequisites
- Node.js 22 or newer.
- Money Lover account credentials for authentic API access.
Installation
npm install
Usage
Launch the MCP server over stdio (suitable for tools such as Claude Code, Cursor, or other MCP hosts):
npm start
MCP Client Configuration
Configure an MCP-compliant client (for example, Claude desktop or Cursor) to invoke the published package via npx and supply credentials through environment variables:
{
"mcpServers": {
"mcp-moneylover": {
"command": "npx",
"args": ["@ferdhika31/moneylover-mcp@latest"],
"env": {
"EMAIL": "alamat-email-anda@example.com",
"PASSWORD": "kata-sandi-anda"
}
}
}
}
The server automatically logs in with the provided credentials and refreshes the session token when required. Supplying a token argument to tools overrides the environment-based authentication.
Tokens resolved through the login tool or environment credentials are cached per-email under ~/.moneylover-mcp/. Cached tokens are reused on subsequent runs and refreshed automatically when the API reports they have expired.
The server registers the following tools:
| Tool | Description | Required Arguments |
|---|---|---|
login |
Retrieves a JWT token using email & password. | email, password |
get_user_info |
Returns profile information tied to the token. | token |
get_wallets |
Lists wallets available to the authenticated user. | token |
get_categories |
Lists categories for a wallet. | token, walletId |
get_transactions |
Retrieves transactions in a date range. | token, walletId, startDate, endDate |
add_transaction |
Creates a new transaction. | token, walletId, categoryId, amount, date (YYYY-MM-DD); optional note, with |
Tokens are not persisted; provide them explicitly when invoking tools other than login.
Library Usage
The underlying REST wrapper is available for reuse:
import { MoneyloverClient } from '@ferdhika31/moneylover-mcp';
const token = await MoneyloverClient.getToken(email, password);
const client = new MoneyloverClient(token);
const wallets = await client.getWallets();
Testing
Run the automated test suite:
npm test
Tests rely on mocked fetch responses and do not hit the live Money Lover service.
Security Notes
- Never commit real credentials or tokens.
- The project intentionally avoids persisting tokens; MCP clients should store secrets securely on their side.
- Cached tokens are stored locally with file permissions restricted to the current user. Delete the
~/.moneylover-mcp/directory if you need to revoke stored sessions.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.