Lunch Flow MCP Server
Enables AI assistants to access financial data from 20,000+ banks across 40+ countries, allowing users to query account balances, transactions, and spending patterns through natural language.
README
Lunch Flow MCP Server
Connect your bank accounts to Claude and other AI assistants. Access financial data from 20,000+ banks across 40+ countries through natural language.
Query balances, transactions, and spending patterns without leaving your conversation - powered by your Lunch Flow account.
Built with the Model Context Protocol and Smithery SDK
Features
This MCP server provides three tools for accessing your financial data:
- lunchflow_list_accounts - Get all your connected bank accounts
- lunchflow_get_account_transactions - Get transaction history for a specific account
- lunchflow_get_account_balance - Get current balance for a specific account
Note: these match Lunch Flow's API.
Quick Start
Prerequisites
- Lunch Flow account: Sign up at lunchflow.app
- Connect your banks: Link your accounts through Lunch Flow
- API key: Get yours at lunchflow.app/destinations
Installation
Install via Smithery:
smithery install @lunchflow/mcp
Or clone and run locally:
git clone https://github.com/lunchflow/mcp.git
cd mcp
npm install
npm run dev
Configuration
For Smithery Deployment
Add to smithery.yaml:
runtime: typescript
Usage Examples
Once configured, you can ask Claude questions like:
- "What are my connected bank accounts?"
- "Show me my transactions from last week"
- "What's my current checking account balance?"
- "How much did I spend on groceries this month?"
- "Compare my spending between Chase and Wells Fargo"
Claude will use the MCP tools to fetch real-time data from your Lunch Flow account.
Development
Building
npm run build
Local Testing
npm run dev
The development server will start and you can test the MCP tools locally.
Bank Coverage
Lunch Flow supports 20,000+ banks across 40+ countries.
Security & Privacy
- ✅ Read-only access to your financial data
- ✅ API keys are securely encrypted
- ✅ No credentials stored in the MCP server
- ✅ All data fetched from your Lunch Flow account
- ✅ Open source for transparency
Support
- Discord: Join our community
- Email: hello@lunchflow.app
License
MIT License - see LICENSE for details
Learn More
- Lunch Flow - Connect your bank accounts
- Smithery - MCP server hosting platform
- Model Context Protocol - MCP specification
- API Documentation - Lunch Flow API docs
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。