Skip to main content
Glama
Rabobank MCP Training Demo

Rabobank MCP Training Demo

Internal MCP Server Demo with uv, FastAPI and FastMCP

A minimal, realistic training project for a 1-hour MCP session with developers.

The project demonstrates how GitHub Copilot in Visual Studio Code can use an internal MCP server to safely access approved internal APIs, documentation and review prompts.

All data is fictional. No real Rabobank data is included.


What this demo contains

rabobank_internal_mcp_uv_demo/
├─ app/
│  ├─ data.py              # Fake internal banking data
│  ├─ internal_api.py      # Internal FastAPI API
│  ├─ mcp_server.py        # MCP server wrapping the internal API
│  ├─ run_api.py           # uv script entrypoint for the API
│  └─ __init__.py
├─ .vscode/
│  ├─ mcp.json             # VS Code MCP config using uv
│  └─ tasks.json           # Optional VS Code tasks
├─ scripts/
│  ├─ demo-calls.ps1       # PowerShell API test calls
│  └─ demo-calls.sh        # Bash API test calls
├─ .env.example
├─ .python-version
├─ pyproject.toml
└─ README.md

Related MCP server: boilerforge

Learning goal

Developers learn that an MCP server can act as a controlled AI-facing layer over internal systems.

GitHub Copilot in VS Code
          │
          ▼
      MCP Client
          │
          ▼
 Internal MCP Server
          │
 ┌────────┼────────┬─────────────┐
 ▼        ▼        ▼             ▼
Internal  API      Policies      Architecture
API       Catalog  / Standards   Checks

Prerequisite: uv

Check if uv is available:

uv --version

Install uv on Windows:

winget install astral-sh.uv

Alternative Windows install:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Setup

From the project folder:

uv sync

This creates the virtual environment and installs dependencies from pyproject.toml.


Training Pages

This repository also contains HTML training material:

  • index.html - self-study guide for MCP and Rabobank Design System context

  • mcp-extension-lab.html - hands-on developer lab for extending this MCP server

  • mcp-extension-trainer-answer-key.html - trainer guide with expected solution and demo flow


Step 1 — Run the internal API

Terminal 1:

uv run bank-api

Open the FastAPI docs:

http://127.0.0.1:8000/docs

Test the health endpoint:

curl http://127.0.0.1:8000/health

Most endpoints require the demo API key:

curl -H "x-api-key: training-demo-key" http://127.0.0.1:8000/customers/CUST-1001

PowerShell alternative:

$Headers = @{ "x-api-key" = "training-demo-key" }
Invoke-RestMethod -Uri "http://127.0.0.1:8000/customers/CUST-1001" -Headers $Headers

Step 2 — Run the MCP server

Normally VS Code starts the MCP server using .vscode/mcp.json.

For a manual smoke test, open Terminal 2:

uv run bank-mcp

The MCP server uses stdio transport, so it may look like it is waiting. That is expected.


Step 3 — Connect in Visual Studio Code

The example config is in:

.vscode/mcp.json

It starts the MCP server with:

uv run bank-mcp

Important: keep the internal API running in Terminal 1.


MCP tools

get_customer_profile(customer_id)

Example IDs:

  • CUST-1001

  • CUST-2002

Example prompt:

Use the internal MCP server to retrieve customer CUST-1001 and summarize the active products.

get_product_info(product_id)

Example IDs:

  • MORTGAGE-FLEX

  • PAYMENT-PLUS

  • BUSINESS-ACCOUNT

Example prompt:

Use the internal MCP server to explain product MORTGAGE-FLEX for a developer who needs to call the product API.

get_api_endpoint_info(api_name)

Example API names:

  • customer-onboarding

  • product-catalog

Example prompt:

Use the internal MCP server to inspect the customer-onboarding API and tell me which endpoint creates a new onboarding case.

run_architecture_check(service_name)

Example prompt:

Run an architecture check for CustomerOnboardingService and summarize the findings as action items.

MCP resources

policy://api-security

Example prompt:

Use the policy://api-security resource and summarize the security requirements for internal APIs.

architecture://event-driven-standards

Example prompt:

Use the architecture://event-driven-standards resource and explain what every event must contain.

MCP prompt

api_security_review_prompt(api_name, endpoint)

Example prompt:

Use the api_security_review_prompt for the customer-onboarding API and endpoint /onboarding/cases.

Trainer flow for 1 hour

0–10 min — Explain MCP

MCP is a standard way to let AI clients use tools, resources and prompts from approved systems.

10–20 min — Show the internal API

Open:

http://127.0.0.1:8000/docs

Show that it represents internal systems:

  • Customer API

  • Product API

  • API catalog

  • Policies

  • Architecture check

20–35 min — Show the MCP server

Open app/mcp_server.py and explain:

  • Tools perform actions or retrieve specific data

  • Resources expose readable knowledge

  • Prompts standardize repeatable tasks

35–50 min — Use GitHub Copilot in VS Code

Run the demo prompts from this README.

50–60 min — Extension exercise

Ask participants to add one new tool:

@mcp.tool
def list_customer_products(customer_id: str) -> list[str]:
    customer = internal_get(f"/customers/{customer_id}")
    return customer["active_products"]

Then ask Copilot:

Use the internal MCP server to list the active products for customer CUST-1001.

Security discussion points

This demo intentionally uses fake data. In a real organization, discuss:

  • Internal allowlist for MCP servers

  • Authentication and authorization

  • Least privilege

  • Audit logging

  • Correlation IDs

  • Output filtering

  • No direct production database access

  • API gateway usage

  • Data classification

  • Separate dev/test/prod environments


Troubleshooting

uv is not recognized

Restart the terminal after installing uv.

API endpoint returns 401

Add the demo API key header:

x-api-key: training-demo-key

MCP server seems stuck

That is normal for stdio MCP servers. It waits for the MCP client.

Port 8000 already in use

Change the port in app/run_api.py or stop the other process.

Available Tools

4 tools
get_api_endpoint_infoB

Retrieve API catalog information for an internal API.

Example API names: customer-onboarding, product-catalog.

Inputs: api_name (required). Returns: object

get_customer_profileA

Retrieve a fake internal customer profile by customer ID.

Example customer IDs: CUST-1001, CUST-2002.

Inputs: customer_id (required). Returns: object

get_product_infoA

Retrieve fake internal product information by product ID.

Example product IDs: MORTGAGE-FLEX, PAYMENT-PLUS, BUSINESS-ACCOUNT.

Inputs: product_id (required). Returns: object

run_architecture_checkC

Run a fake internal architecture check for a service.

Inputs: service_name (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct entity or action: customer profile, product info, API endpoint info, and architecture check. There is no overlap in purpose.

    Naming Consistency4/5

    Three tools use the get_ prefix (get_customer_profile, get_product_info, get_api_endpoint_info), while one uses run_ (run_architecture_check). The pattern is mostly consistent but has a minor deviation.

    Tool Count5/5

    With 4 tools, the server is well-scoped for a training demo. Each tool covers a different aspect, and the count is appropriate without being bloated or thin.

    Completeness4/5

    The tools cover the main read-only operations for a demo (customer, product, API info, and architecture check). Missing CRUD operations or additional resources like accounts/transactions could be considered gaps, but the demo purpose is adequately served.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A production-grade MCP server that exposes real-time banking data replicated via Oracle GoldenGate CDC as structured tools for AI agents, enabling read, score, and write operations on customer, account, transaction, and alert data.
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A production-grade MCP server for a fictional digital bank, exposing tools for an AI copilot to service customers across the full risk spectrum from read-only lookups to money movement and destructive admin actions, with OAuth 2.1 security and a realistic dataset.
      23 npm
      1
      -
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for AWS Payment Cryptography that gives AI coding assistants direct access to the APC control plane and data plane, with embedded knowledge of payment standards, HSM vendor command sets, and PCI PIN v3.1 compliance requirements.
      58
      2
      Apache 2.0