monter-mcp

monter-mcp

Enables local analysis of personal finance data from a Monter JSON export, answering questions about spending, subscriptions, debts, and more via MCP-capable assistants without any cloud servers.

Category
访问服务器

README

monter-mcp

Ask any MCP-capable assistant about your own money - locally, from the export file you made in Monter.

"How much did I spend in July?"
"What do I pay for on autopilot every month?"
"How much does my credit card quietly cost me per month?"
"Is any of my cash sitting idle below market rate?"

Every answer is plain arithmetic over your own numbers. No server, no account, no telemetry - this package reads one JSON file on your disk and does math.

Setup

  1. In Monter on your iPhone: Profile → Export your data (JSON), then AirDrop the file to your computer (e.g. into ~/Documents).
  2. Add the server to your assistant.

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "monter": {
      "command": "npx",
      "args": ["-y", "monter-mcp", "--export", "/Users/you/Documents/monter-export-2026-08-21.json"]
    }
  }
}

Claude Code:

claude mcp add monter -- npx -y monter-mcp --export ~/Documents/monter-export-2026-08-21.json

Re-export any time; the server picks up the fresh file automatically (it re-reads on change). Point the config at a stable path like ~/Documents/monter-export.json if you prefer renaming each export once.

Tools

Tool What it answers
snapshot_meta How fresh the export is and what it contains
spending Total + per-category spending for a month or date range
income Total income for a period
transactions_search Find transactions by merchant or category
subscriptions_overview Recurring costs normalised to monthly
debts_overview Balances, APRs, and interest per month
wallets_overview Balances per wallet and per currency
idle_cash_check Cash above one month of expenses earning under 3%
insurance_overview Premium total and its share of monthly expenses
goals_overview Savings goals and progress
checkins_stats Check-in streak and points
health_score The app's 0-100 financial health score with components *
money_leaks Detected leaks, their monthly cost, and resolved wins *
freedom_day The Freedom Day estimate from the user's plan *
profile_overview Stated setup: expenses, cushion target, income sources
budgets_overview Budget limits vs actual spending

* Needs an export made from Monter 1.1+ (schemaVersion 2, with the computed layer). Older exports still work for everything else.

Privacy

Your export never leaves your machine through this package: the server is local, makes no network calls, and contains no analytics of any kind. One honest caveat: the assistant you connect it to is your choice - anything it reads through these tools travels through that assistant's provider under your agreement with them.

Figures are your own data, arithmetically rearranged. Nothing here is financial advice.

Development

npm install
npm test   # builds and runs smoke tests against test/fixture.json

MIT © MB Utilab

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选