lunchmoney-mcp-v2
Enables managing personal finances through the Lunch Money API, including transactions, categories, budgets, and accounts via natural language commands.
README
lunchmoney-mcp-v2
MCP server for the Lunch Money API v2. First MCP server built on the v2 API.
Features
- 14 tools covering read, CRUD, and advanced operations
- Hydrated responses: category, tag, and account names instead of raw IDs
- Smart caching: categories, tags, and accounts cached at startup, auto-refreshed after mutations
- Type-safe: generated from the official OpenAPI spec via
openapi-typescript
Setup
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"lunchmoney": {
"command": "npx",
"args": ["lunchmoney-mcp-v2"],
"env": {
"LUNCHMONEY_TOKEN": "your-api-token-here"
}
}
}
}
Claude Code
Add to .mcp.json in your project or ~/.claude/mcp.json globally:
{
"mcpServers": {
"lunchmoney": {
"command": "npx",
"args": ["lunchmoney-mcp-v2"],
"env": {
"LUNCHMONEY_TOKEN": "your-api-token-here"
}
}
}
}
Get your API token from Lunch Money Developer settings.
Tools
Read
| Tool | Description |
|---|---|
get_user |
Account info (name, email, currency) |
list_transactions |
List/search transactions with filters, or look up by ID |
list_categories |
All categories (nested or flat view) |
list_tags |
All tags |
get_accounts |
Manual + synced accounts with balances |
get_summary |
Budget summary with income/spending/per-category breakdown |
get_recurring |
Recurring items (subscriptions, bills, income) |
CRUD
| Tool | Actions | Description |
|---|---|---|
manage_transaction |
create, update, delete | Single transaction operations |
manage_category |
create, update, delete | Category management (force delete with dependency info) |
manage_tag |
create, update, delete | Tag management (force delete with dependency info) |
manage_account |
create, update, delete | Manual account management (Plaid accounts are read-only) |
Advanced
| Tool | Actions | Description |
|---|---|---|
bulk_update_transactions |
— | Batch update up to 500 transactions at once |
split_transaction |
split, unsplit | Split a transaction into parts or restore the original |
group_transactions |
group, ungroup | Combine transactions into a group or restore originals |
Example prompts
Once connected, just ask your LLM naturally:
Reviewing & organizing
- "Show me all unreviewed transactions from this month"
- "Categorize all my Amazon transactions as Shopping"
- "What did I spend on groceries last week?"
- "Mark these 5 transactions as reviewed"
Budget overview
- "Give me a spending summary for January"
- "What are my recurring expenses?"
- "How much do I have in each account?"
Managing transactions
- "Add a $45 transaction for dinner at Nobu yesterday"
- "Split that $120 Costco transaction into $80 groceries and $40 household"
- "Group these three Uber transactions into one"
- "Delete the duplicate transaction I just created"
Organizing
- "Create a new category called Side Projects"
- "Tag these transactions with travel"
- "Show me all my categories with their IDs"
- "Rename the Dining Out category to Restaurants"
Development
npm install
npm run build
npm start
Regenerate types from the OpenAPI spec:
npm run generate:types
Architecture
src/
index.ts Entry point — registers tools, initializes cache
client.ts openapi-fetch client + error handling
cache.ts In-memory cache for categories, tags, accounts
format.ts Text formatters for all response types
types.ts Generated from @lunch-money/v2-api-spec
tools/
user.ts get_user
transactions.ts list_transactions, manage_transaction, bulk_update, split, group
categories.ts list_categories, manage_category
tags.ts list_tags, manage_tag
accounts.ts get_accounts, manage_account
summary.ts get_summary
recurring.ts get_recurring
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。