juandisay/signals-financial-tracker
If you are the rightful owner of signals-financial-tracker and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Signals Finance Tracker is a Model Context Protocol (MCP) server designed to help users manage their personal finances by tracking expenses, income, and budgets.
Signals Finance Tracker
A Model Context Protocol (MCP) server for tracking personal finances: expenses, income, and budget summaries.
Features
- Track expenses with categories, tags, and payment methods
- Record income from various sources
- Set and monitor budgets
- Generate financial reports and insights
- MCP integration for AI assistants
Installation
Using pip
pip install signals-finance-tracker
From source
git clone https://github.com/juandisay/signals-financial-tracker.git
cd signals-financial-tracker
pip install -e .
Global installation for uvx
To install the package globally so it can be used with the uvx
command:
# Using the provided script
./install-global.sh
# Or manually
python -m build
pip install dist/signals_finance_tracker-*.whl
Usage
CLI Interface
The package provides a command-line interface for managing your finances:
# Show help
finance --help
# Add an expense
finance expense add --amount 25.99 --category "Food" --description "Grocery shopping"
# List expenses
finance expense list
# Add income
finance income add --amount 1000 --source "Salary" --description "Monthly salary"
# Show budget status
finance budget status
Running as an MCP Server
To run as an MCP server for integration with AI assistants:
# Using the provided script (recommended)
./run-finance-mcp.sh
# Using uvx directly with the local package
uvx --with-editable . signals-finance-tracker
# If the package is installed globally
uvx signals-finance-tracker
Environment Variables
You can configure the application using environment variables:
FINANCE_DATA_DIR
: Directory for storing application data (default:~/.signals/finance
)FINANCE_DB_URL
: Database URL (default:sqlite:///{data_dir}/finance.db
)FINANCE_LOG_LEVEL
: Logging level (default:INFO
)FINANCE_SEED_DEFAULTS
: Whether to seed default data (default:false
)MCP_TRANSPORT
: Transport method for MCP (default:stdio
)
MCP Integration
This package implements the Model Context Protocol (MCP) for integration with AI assistants. When running as an MCP server, it provides the following tools:
- Query expenses with filters
- Query income entries
- Query budgets
- Generate financial reports
- Analyze expense patterns
- Analyze budget performance
- Generate financial advice
To use with an MCP-enabled assistant:
- Start the MCP server:
./run-finance-mcp.sh
- Connect your AI assistant to the MCP server
- Ask the assistant about your finances
Development
# Install development dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Format code
black src tests
isort src tests
# Type checking
mypy src
License
MIT