MCP Banking Server
A minimal banking system MCP server that allows account management, deposits, withdrawals, balance inquiries, and transaction history via REST endpoints.
README
MCP Server - Python FastAPI
Overview
This is a MCP (Minimal Core Platform) Server implemented in Python using FastAPI. It simulates a basic banking system with endpoints for account management, deposits, withdrawals, balance inquiries, and transaction history.
Hosted URL
https://mcp-server-m5d2.onrender.com
Cloud Provider
Render - Publicly accessible deployment.
Technology Stack
- Python 3.13
- FastAPI
- Uvicorn
- SQLAlchemy (SQLite/PostgreSQL compatible)
- Pydantic
- python-dotenv
Endpoints
1. Create Account
POST /account
Creates a new bank account.
Request Body Example:
{
"name": "John Doe",
"email": "john@example.com"
}
Response Example:
{
"name": "alex roy",
"email": "example@gmail.com",
"created_at": "2025-12-27T17:43:36",
"balance": 0,
"id": "05997aae-a545-4157-9118-99fd2ec7b4c7"
}
2. Deposit
POST /deposit/{account_id}
Adds funds to an existing account.
Request Body Example:
{
"amount": 500.0
}
Response Example:
{
"account_id": "uuid",
"balance": 500.0
}
3. Withdraw
POST /withdraw/{account_id}
Removes funds from an existing account.
Request Body Example:
{
"amount": 100.0
}
Response Example:
{
"account_id": "uuid",
"balance": 400.0
}
4. Balance Inquiry
GET /balance/{account_id}
Retrieves the current balance of the account.
Response Example:
{
"account_id": "uuid",
"balance": 400.0
}
5. Transaction History
GET /transactions/{account_id}
Returns recent transactions for the account.
Response Example:
[
{
"transaction_id": "uuid",
"type": "deposit",
"amount": 500.0,
"timestamp": "2025-12-27T12:00:00"
},
{
"transaction_id": "uuid",
"type": "withdraw",
"amount": 100.0,
"timestamp": "2025-12-27T12:10:00"
}
]
Database & ACID Properties
The MCP Server uses SQLAlchemy to interact with a relational database (SQLite by default). The database logic ensures the operations:
- Isolation: Simultaneous transactions on different accounts are isolated; concurrent operations do not interfere.
- Durability: Once a transaction is committed, it persists even if the server crashes.
Running Locally
Prerequisites
- Python 3.13
- pip
Install Dependencies
pip install -r requirements.txt
Start Server
uvicorn main:app --host 0.0.0.0 --port 8000
Visit http://127.0.0.1:8000/docs for Swagger UI.
ArmorIQ Scanning
- Tested with ArmorIQ Sentry VS Code extension (
Sentry-MCP-Endpoint-Scan,Sentry-Scan-WorkSpace-For-MCP-Security-Issue) - Tested with ArmorIQ Landing Page scanner
- Endpoints are exposed publicly for the purpose of security scanning
GitHub Repository
https://github.com/shreyash1231/MCP-Server.git
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.