EzBookkeeping MCP Server
Enables AI assistants to interact with EzBookkeeping for personal finance management through natural language, including adding transactions, checking balances, and generating reports.
README
EzBookkeeping MCP Server
A comprehensive Model Context Protocol (MCP) server that integrates AI assistants with EzBookkeeping, enabling natural language interactions for personal finance management.
Note: This project is currently in active development. The server currently includes example/demo implementations. Full integration with the EzBookkeeping API is planned based on the comprehensive research documented in this repository.
What is This?
This MCP server allows AI assistants like Claude to interact with your EzBookkeeping instance through natural language. Ask Claude to add transactions, check balances, analyze spending patterns, and generate financial reports - all through conversation.
Example interactions:
- "Add a $45 grocery expense to my checking account"
- "Show me my spending trends for this month"
- "What's my total balance across all accounts?"
- "Create a budget report for the last quarter"
Features
Current (Demo Implementation)
Tools (Write Operations):
add_transaction- Add income or expense transactionscalculate_balance- Calculate balance from transaction lists
Resources (Read Operations):
bookkeeping://summary/{period}- Get financial summary for a period
Prompts (AI Templates):
create_financial_report- Generate financial report prompts
Planned (Full EzBookkeeping Integration)
Based on comprehensive API research (99 endpoints documented):
Transaction Management:
- Create, update, delete transactions
- Batch operations
- AI-powered receipt recognition
- Transaction statistics and trends
- Import/export functionality
Account Management:
- Manage accounts across 9 types (Cash, Credit Card, Investment, etc.)
- Multi-currency support
- Hierarchical accounts with sub-accounts
Organization:
- Category and tag management
- Transaction templates
- Recurring transactions
Analytics:
- Spending analysis and trends
- Budget tracking
- Financial summaries and reports
See MCP_SERVER_DESIGN.md for the complete architecture plan.
Installation
Prerequisites
- Python 3.10 or higher
- uv package manager
- (Optional) An EzBookkeeping instance for full API integration
Quick Start
- Clone the repository:
git clone https://github.com/theanirudhvyas/ezbookkeeping_mcp_server.git
cd ezbookkeeping_mcp_server
- Install dependencies:
uv sync
- Configure (for full EzBookkeeping integration):
cp .env.example .env
# Edit .env with your EzBookkeeping instance URL and API token
- Test the server:
uv run mcp dev main.py
This opens the MCP Inspector at http://localhost:5173 for interactive testing.
Configuration
For full EzBookkeeping API integration, configure the following environment variables:
# Required
EZBOOKKEEPING_URL=https://your-instance.com
EZBOOKKEEPING_TOKEN=your_api_token_here
# Optional
EZBOOKKEEPING_TIMEZONE_OFFSET=0
EZBOOKKEEPING_DEFAULT_CURRENCY=USD
See .env.example for a complete configuration template.
Usage with Claude Desktop
Automatic Installation
uv run mcp install main.py
Manual Configuration
Add to your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ezbookkeeping": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/ezbookkeeping_mcp_server",
"run",
"mcp",
"run",
"main.py"
],
"env": {
"EZBOOKKEEPING_URL": "https://your-instance.com",
"EZBOOKKEEPING_TOKEN": "your_token"
}
}
}
}
Restart Claude Desktop to load the server.
Development
Running the MCP Inspector
The MCP Inspector provides an interactive web interface for testing:
uv run mcp dev main.py
Opens at http://localhost:5173 with:
- Tool testing with parameter forms
- Resource browsing
- Prompt generation
- Real-time request/response logs
Running Tests
# Install dev dependencies
uv sync --all-extras
# Run tests
uv run pytest
# Run with coverage
uv run pytest --cov=. --cov-report=html
Usage Examples
Adding a Transaction
# Using the add_transaction tool
add_transaction(
amount=50.00,
description="Grocery shopping",
category="food",
transaction_type="expense"
)
Calculating Balance
# Using the calculate_balance tool
transactions = [
{"amount": 1000, "type": "income"},
{"amount": 50, "type": "expense"},
{"amount": 30, "type": "expense"}
]
calculate_balance(transactions)
# Returns: {"income": 1000, "expenses": 80, "balance": 920}
Getting a Summary
Access the resource URI:
bookkeeping://summary/month
Project Structure
ezbookkeeping_mcp_server/
├── main.py # MCP server implementation
├── pyproject.toml # Project configuration & dependencies
├── API_DOCUMENTATION.md # Complete EzBookkeeping API reference (99 endpoints)
├── MCP_SERVER_DESIGN.md # Architecture and implementation plan
├── QUICKSTART.md # Quick reference guide
├── README.md # This file
├── CONTRIBUTING.md # Contribution guidelines
├── CHANGELOG.md # Version history
├── LICENSE # MIT License
├── .env.example # Environment configuration template
├── .claude/ # Claude Code configuration
│ └── CLAUDE.md # MCP development best practices
├── tests/ # Test suite (planned)
└── .venv/ # Virtual environment (gitignored)
Documentation
- API_DOCUMENTATION.md - Complete EzBookkeeping API reference with all 99 endpoints
- MCP_SERVER_DESIGN.md - Comprehensive architecture, design decisions, and roadmap
- QUICKSTART.md - Quick start guide for common operations
- .claude/CLAUDE.md - MCP server development best practices
Roadmap
Phase 1: Foundation (Planned)
- [ ] HTTP client with authentication
- [ ] Token management and refresh
- [ ] Error handling and retry logic
- [ ] Timezone support
Phase 2: Core Features (Planned)
- [ ] Transaction tools (add, update, delete)
- [ ] Account resources (list, get)
- [ ] Transaction resources (list, statistics)
- [ ] Category/tag resources
Phase 3: Advanced Features (Planned)
- [ ] Batch operations
- [ ] Transaction templates
- [ ] AI receipt recognition integration
- [ ] Export functionality
- [ ] Exchange rate management
Phase 4: Intelligence (Planned)
- [ ] Spending analysis prompts
- [ ] Budget tracking prompts
- [ ] Financial insights generation
- [ ] Duplicate detection
- [ ] Category suggestions
See MCP_SERVER_DESIGN.md for detailed implementation plan.
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
Areas for Contribution
- Implementing API endpoints
- Adding tests
- Improving error handling
- Documentation improvements
- Feature suggestions
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- EzBookkeeping: Official Documentation
Related Projects
- EzBookkeeping - The personal bookkeeping application
- Model Context Protocol - MCP specification and documentation
- Python MCP SDK - Official Python SDK
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- EzBookkeeping by @mayswind for the excellent personal finance application
- Model Context Protocol by Anthropic for the integration framework
- The MCP community for tools and resources
Disclaimer
This project is not officially affiliated with or endorsed by the EzBookkeeping project. It is an independent integration built using EzBookkeeping's public HTTP API.
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.