Banking MCP Server (MongoDB Backend)
Enables basic banking operations such as account creation, deposits, withdrawals, and transfers using MongoDB for persistent storage.
README
Banking MCP Server (MongoDB Backend)
A simple Model Context Protocol (MCP) server for basic banking operations (CRUD) using MongoDB as the backend. This project demonstrates how to build an MCP server for account management and money transfers.
Features
- Create, delete, and list accounts
- Deposit, withdraw, and transfer funds
- Persistent storage with MongoDB
Prerequisites
- Python 3.8+
- MongoDB (local or cloud)
- uv (recommended)
Setup
- Clone the repository
git clone <repository-url> cd banking-mcp-server-mdb - Install dependencies
uv pip install -r requirements.txt - Configure MongoDB
Create a
.envfile in the project root:
Start your MongoDB server if not already running.MONGO_URI=mongodb://localhost:27017 MONGO_DB=money_transfer_db - Start the MCP server (Note: This doesn't do anything by itself. It's meant to be called via MCP Clients or toold like ClaudeDesktop)
./start_banking_mcp_server_mdb.sh
Claude Desktop Configuration
Add this to your claude_desktop_config.json to use the server:
"mcpServers": {
"bank_accounts": {
"command": "/absolute/path/to/banking-mcp-server-mdb/start_banking_mcp_server_mdb.sh",
"args": []
}
}
Replace the path with your actual project location.
Available Tools
create_account(username, balance=0.0): Create a new accountdelete_account(username): Delete an accountget_account(username): Get account infolist_accounts(): List all accountsdeposit(username, amount): Deposit fundswithdraw(username, amount): Withdraw fundstransfer(from_user, to_user, amount): Transfer funds between accounts
Example Usage
Ask Claude:
- Create an account:
Create a bank account for Alice with $100. - Transfer funds:
Transfer $50 from Alice to Bob. - List accounts:
Show all accounts.
This project is for demonstration purposes only.
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。