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
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.