finanze-mcp
Enables AI assistants to read and query a Finanze self-hosted portfolio manager using natural language, including net worth, positions, and financial calculations.
README
finanze-mcp
An MCP server for Finanze, the self-hosted portfolio manager.
It lets an AI assistant (Claude Code, Claude Desktop…) read your Finanze portfolio and run financial calculations in plain language — "what's my net worth?", "show my crypto positions", "simulate this mortgage".
It talks to your local Finanze backend over its HTTP API and exposes a read-only tool set (plus optional live-refresh). It never changes your data.
What it can do
- See your portfolio: positions, contributions, transactions, net-worth timeline, history.
- Markets: exchange & Euribor rates, stock/fund/ETF lookup, crypto asset search.
- Real estate & cash flows: properties, recurring and pending flows.
- Calculations: loan/mortgage amortization, savings projections, portfolio forecast.
- Optional live refresh (off by default): trigger a data fetch from your connected banks, brokers and crypto wallets.
Requirements
- A running Finanze backend (default
http://localhost:7592). - Python 3.11+.
Install
git clone https://github.com/adriadam10/finanze-mcp.git
cd finanze-mcp
pip install -e .
Configure
Copy the example env file and fill in your Finanze credentials (used to unlock the local DB):
cp .env.example .env
FINANZE_BASE_URL=http://localhost:7592
FINANZE_USERNAME=your-username
FINANZE_PASSWORD=your-password
Use with Claude Code
From the project folder:
claude mcp add --scope user --transport stdio finanze -- python -m finanze_mcp
Or rely on the bundled .mcp.json (project scope): open Claude Code in this directory with
FINANZE_USERNAME / FINANZE_PASSWORD exported, and it's picked up automatically.
Then just ask Claude things like "what's my current net worth?".
Claude Desktop: add the same
command/args/envto yourclaude_desktop_config.jsoninstead (Claude Desktop doesn't use.mcp.json).
Optional: live data refresh
Disabled by default. To expose the fetch tools (they make real calls to your banks/brokers and may require 2FA), set:
FINANZE_ENABLE_FETCH=true
Development
pip install -e ".[dev]"
pytest # tests
ruff check . # lint
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。