zenmoney-mcp
MCP server for ZenMoney that enables AI clients to read and manage personal finance data (accounts, categories, transactions, etc.) via natural language.
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
- Node.js >= 18
- A ZenMoney account
- API token from zerro.app/token
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:
- Sync first — "Sync my ZenMoney data"
- Browse — "Show me my accounts", "List my categories"
- Query — "Show expenses for the last 7 days", "List transactions from January 1–31", "How much did I spend on groceries?"
- Add transactions — "Add a 500 RUB expense for coffee today"
- Transfer — "Transfer 1000 USD from Checking to Euro Card, received 920 EUR"
- Review — "Review July for duplicate, uncategorized, and unusually large transactions"
- Organize categories — "Create an expense category named Utilities under Housing"
- 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
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。