VANDAMMCP Retrofit
Let customers use your productfrom their AI assistant.
A working connection between your software and customers’ AI assistants. They can ask for agreed actions, such as finding an order, while your product continues to control which accounts, records and changes they may access.
$12,800 two weeks · plus hosting
Mara at Northwind, in 
Claude
The MCP connection
Atlas & Co. ordering system
Where is our order 1048?
- account
- northwind
- scopes
- orders:read stock:read
tools/callid 7
"name" "get_order"
"arguments" { "order_id" "1048" }
needs orders:read
Allowed. Northwind may read its own orders.
result"isError" false
"text" "Order 1048: packed, 24 cases, ships 28 Oct"
1046Order, NorthwindDelivered 21 Oct1048Order, NorthwindPacked, 24 cases, ships 28 Oct1050Order, Hollis FoodsAnother accountOL-1000Stock, olive oil 1 L112 casesRV-500Stock, red wine vinegar 0.5 L38 casesOL-1000Price, Northwind terms$21.40 a case
Claude
Order 1048 is packed. All 24 cases leave the warehouse on Wednesday 28 October.
Within a year, every major assistant spoke MCP.
- 10,000+
- active public MCP servers by December 2025, when
Anthropic handed the protocol to a Linux Foundation fund backed by 
OpenAI, Google, 
Microsoft and AWS. - 97M
- monthly downloads of the MCP software kits at that point, used inside
ChatGPT, 
Gemini, 
Copilot, Cursor and VS Code. Anthropic. - 4.5
- months from Anthropic’s launch in November 2024 to support from OpenAI and Google DeepMind.
MCP is emerging as a new AI interface. In the near-future, MCP may become the default way, or in some cases the only way, people, businesses, and code discover and interact with services.
So no, your login page won’t stay the only way into your product.
Make your product available where work begins.
A customer who already works in an AI assistant wants to find an order or check stock by asking there, without opening your product in another tab. If your software cannot answer, the assistant guesses or sends them elsewhere.
Anthropic released MCP, the Model Context Protocol, as an open standard in November 2024, and 
Block was among the first companies to build on it. It lets an assistant call defined actions in your software. We build that connection around a small, agreed set of actions, and your product keeps its own permissions: a customer who can read orders still cannot change one because the request came through an assistant.
What changes for customers and for your team.
A signed-in customer asks their assistant where an order is or whether an item is in stock. The assistant calls one of the agreed actions, your product checks the account and its permissions, and the answer comes from your own records. A request outside those permissions is refused with a reason the customer can act on.
Your team works from the action list: each action with its description, the information it needs and who may call it. Before a change goes live, the repeatable tests run complete requests, disallowed actions and failure cases, so you see whether the change affects what an assistant can reach.
What every connection is built from.
Your product and your actions differ. The service around them has the same eight parts.
Action list
The small, agreed set of tasks customers can complete from their assistant.
Action descriptions
What each action does and the information it needs, written so an assistant calls it correctly.
Authentication
Customers sign in with their own account, and each gets customer-specific keys.
Account permissions
Your product’s roles and account boundaries applied to every call.
Rate limits
A ceiling on how often each customer’s assistant can call your product.
Refusal messages
A clear reason for every refused or failed request, so the assistant can explain it.
Conversation tests
Repeatable checks for complete requests, disallowed actions and failure cases.
Operating guide
How your technical team runs, updates and maintains the service.
How the connection is delivered.
Choose the useful actions
We agree which tasks customers should be able to complete from their assistant. Each action gets a clear description, required information and an explicit access boundary tied to your product.
Actions for assistants - Check order statusany signed-in customer
- Book a delivery slotaccount owner
- Download an invoicebilling role
- Change pricesnever exposed
Build and test the connection
We build the MCP service, authenticate customers and apply account permissions. Tests cover complete requests, disallowed actions and failure cases, including how an assistant should explain an unsuccessful request.
Test run · 48 cases - Complete requests22 passed
- Disallowed actions refused14 passed
- Failure explained to the user11 passed
- Expired token1 fixed, retest
Launch with operating instructions
We deploy the service on your infrastructure or ours. You receive the running connection, action documentation, repeatable tests and the instructions your technical team needs to operate and maintain it.
atlas-mcp · deployed tools: 3 auth: OAuth 2.1clients:Claude, ChatGPT, Copilot- +
GET /orders/{id}/status - +
POST /deliveries/slots - +
GET /invoices/{id}.pdf
Live in two weeks.
Looked after when you want.
You own the service, the tests and the documentation. Customers will ask for new actions and your product will change, so after launch we can stay on for a monthly fee.
Hosting
We run the MCP service on your infrastructure or ours.
Test runs
The conversation tests run again after each change to your product or to the actions.
New actions
New actions scoped, built and tested with your product team, a few at a time.
Check-ins
A monthly session with your product team on open requests and which action to add next.
What you
receive.
MCP server
Customer-specific keys, authentication and rate limits.
Conversation tests
Repeatable checks for the actions your users take.
Tool documentation
Action descriptions, parameters and access requirements.
Deployment
A running service and its operating guide.
MCP servers in production: Douano, Marketing, Kompas and NextCV. Douano runs orders and stock on a live sales stack.
Where the retrofit leads.
Each next step has its own service.
Every B2B software company is (or should be) building a "headless" version of their product. One that can be used by agents.
HubSpotApril 2026Source Before you ask.
Can an assistant do more than the customer can in our product?
No. Every call runs under the customer’s own account and permissions. A customer who can read orders still cannot change one through an assistant.
Do we have to expose our whole API?
No. We start from a small, agreed set of actions. Anything outside that list, such as changing prices, is never exposed.
Which assistants can connect?
Claude, ChatGPT and other clients that support MCP. Customers connect with their own account in your product.
Where does the service run, and who maintains it?
On your infrastructure or ours. You receive the operating guide and the tests, so your technical team can run it, or we can look after it monthly.