Blackwell Bank Card Hub MCP
Enables users to explore and manage banking card features including product discovery, comparison, eligibility checks, spend insights, merchant offers, travel notices, card controls, and digital wallet provisioning.
README
Blackwell Bank Card Hub MCP App
A ChatGPT Apps / MCP demo for a retail banking card experience. The app opens on a Card Hub and lets users move between product discovery, comparison, eligibility, spend insights, merchant offers, travel notices, card controls, and wallet provisioning.
Public deployment:
https://bank.myareareport.com/mcp
The VPS deployment is isolated from the existing mcp.myareareport.com service. This app runs in its own Docker Compose service named mcp-bank and is bound locally on 127.0.0.1:3002.
Features
- Card Hub-first embedded UI with persistent customer/card context.
- Product catalogue with card details, rewards calculator, balance transfer estimator, and eligibility flow.
- Mobile tabs for
Cards,Compare, andEligibility. - Visual comparison summary for travel, everyday spend, and credit building.
- Servicing tools for spend insights, merchant offers, travel notices, card controls, and digital wallet.
- App-only MCP tools for UI navigation and interactive state changes.
- Streamable HTTP transport for hosted MCP clients.
- Stdio transport for local desktop MCP clients.
Requirements
- Node.js 22 recommended, Node.js 18+ minimum.
- npm.
- Docker and Docker Compose for VPS/container deployment.
Local Setup
git clone https://github.com/meabs/mcp-app-ui-bank.git
cd mcp-app-ui-bank
npm install
npm run build
npm start
The local MCP endpoint runs at:
http://localhost:3001/mcp
For development watch mode:
npm run dev
Scripts
| Command | Purpose |
|---|---|
npm run build |
Build the single-file app bundle with Vite. |
npm start |
Build and start the Streamable HTTP MCP server. |
npm run start:stdio |
Start the MCP server over stdio. |
npm run dev |
Watch-build the UI and restart the server on changes. |
npm test |
Run the Node test suite. |
Testing
Run the automated tests:
npm test
Build the app:
npm run build
Check production dependencies:
npm audit --omit=dev
Verify a running MCP endpoint:
curl -fsS http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1"}},"id":1}'
List tools:
curl -fsS http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":2}'
Public MCP URL
Use this endpoint when adding the app to a ChatGPT MCP-capable project or tool configuration:
https://bank.myareareport.com/mcp
The deployed server should report:
Blackwell Bank Card Services
Docker Deployment
The included Compose file builds the app and exposes the container only on localhost:
docker compose up -d --build
Container mapping:
mcp-bank: 127.0.0.1:3002 -> 3001/tcp
Cloudflare Tunnel routes bank.myareareport.com to http://localhost:3002.
Key Files
| File | Purpose |
|---|---|
src/index.js |
Streamable HTTP and stdio transport setup. |
src/server.js |
MCP tool and resource registrations. |
src/demo-data.js |
Demo card, hub, eligibility, spend, wallet, and offer data. |
src/mcp-app.html |
Embedded app shell and view containers. |
src/mcp-app.js |
App state, routing, host integration, and product flow rendering. |
src/feature-views.js |
Hub, compare, servicing, calculator, and journey renderers. |
src/mcp-app.css |
Embedded app visual system and responsive layout. |
docker-compose.yml |
Isolated VPS service definition for mcp-bank. |
Current Verification
Latest known-good checks:
npm test
npm run build
npm audit --omit=dev
The deployed endpoint at https://bank.myareareport.com/mcp initializes and exposes the Blackwell Bank tools.
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.