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.
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。