zenmoney-mcp

zenmoney-mcp

MCP server for ZenMoney that enables AI clients to read and manage personal finance data (accounts, categories, transactions, etc.) via natural language.

Category
访问服务器

README

zenmoney-mcp

MCP server for ZenMoney — access your personal finance data from any MCP-compatible AI client (Claude Desktop, Cursor, etc.).

Features

Tool Description
sync_data Sync data with ZenMoney (run first)
list_accounts List wallets, cards, and cash accounts
list_categories List expense/income categories with hierarchy
list_merchants List known merchants/payees
list_transactions List and filter recent transactions
add_expense Add an expense transaction
add_income Add an income transaction
add_transfer Transfer money between accounts (including cross-currency)
suggest_category Get auto-suggested category for a payee
review_transactions Find likely duplicates, uncategorized entries, and unusually large transactions
change_transaction_category Replace the category of an existing transaction
update_transaction_details Update a transaction's payee/payer or comment
delete_transaction Delete an existing transaction
create_category Create an income, expense, or combined category
update_category Rename a category or change its hierarchy and budget settings
delete_category Delete an unused leaf category
merge_categories Move transactions into another category and remove the source category

All tools that modify ZenMoney advertise MCP write/destructive annotations so compatible clients can request approval before executing them. Approval behavior still depends on the MCP client's policy and configuration.

Prerequisites

Quick start

No cloning or building needed — just add to your MCP client config:

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "zenmoney": {
      "command": "npx",
      "args": ["-y", "zenmoney-mcp"],
      "env": {
        "ZENMONEY_TOKEN": "your_token_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "zenmoney": {
      "command": "npx",
      "args": ["-y", "zenmoney-mcp"],
      "env": {
        "ZENMONEY_TOKEN": "your_token_here"
      }
    }
  }
}

Claude Code

claude mcp add zenmoney -- npx -y zenmoney-mcp

Replace your_token_here with your token from zerro.app/token.

Claude Desktop (MCPB bundle)

If you prefer a one-click install without editing JSON, build a .mcpb bundle and drag it into Claude Desktop → Settings → Extensions:

npm install
npm run pack:mcpb
# → dist/zenmoney-mcp-<version>.mcpb

On install, Claude Desktop will prompt for your ZenMoney token (stored in the OS keychain).

From source

git clone https://github.com/a-tarasoff/zenmoney-mcp.git
cd zenmoney-mcp
npm install
npm run build
cp .env.example .env  # add your token

Usage

Once configured, start a conversation and ask your AI client to:

  1. Sync first — "Sync my ZenMoney data"
  2. Browse — "Show me my accounts", "List my categories"
  3. Query — "Show expenses for the last 7 days", "List transactions from January 1–31", "How much did I spend on groceries?"
  4. Add transactions — "Add a 500 RUB expense for coffee today"
  5. Transfer — "Transfer 1000 USD from Checking to Euro Card, received 920 EUR"
  6. Review — "Review July for duplicate, uncategorized, and unusually large transactions"
  7. Organize categories — "Create an expense category named Utilities under Housing"
  8. Clean up — "Change this transaction to Groceries" or "Merge Dining Out into Food"

Transaction listing and review tools return transaction IDs. Use those IDs for precise edits instead of relying on ambiguous dates, amounts, or payee names.

Contributing

PRs welcome! Feel free to open issues for bugs or feature requests.

License

MIT

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