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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.