How to turn your expertise into an MCP, without writing code

A client is drafting a contract in Claude and asks which rights to hand over. The assistant gives the answer any assistant would give. You would have answered differently, and you have, many times, in emails that client will never see.

An MCP built from your decisions puts those answers where the client’s assistant can read them. This guide covers what you need, what your own AI does, and where it stops for you. No code is required.

What an MCP is, in one paragraph

MCP (Model Context Protocol) is the open standard AI apps use to plug in outside tools. Claude, ChatGPT, and Cursor support it. A person pastes one link once, and from then on their assistant can call that link in the middle of a conversation and use what comes back.

Most MCPs connect an assistant to software, such as a calendar or a database. The one you will build connects it to how you decide.

What goes into it

Decisions you have already made, each with four parts:

• The situation. What was on the table, in general terms.
• The decision. What you decided.
• The reason. Why, as you would say it. This is the part that transfers to new cases.
• What would have changed it. The condition under which you would have gone the other way.

Include the ordinary decisions as well as the unusual ones. A collection of exceptions gives a misleading picture of your usual practice. The decision log guide has a worked entry and questions for recalling calls you never wrote down.

Where the decisions come from

You probably have them already, scattered across:

• emails and messages where you explained a decision to a client or a colleague;
• proposals you accepted or turned down, with your notes;
• post-mortems, review comments, or meeting notes;
• the answer you give every time someone asks you the same question.

What to leave out is just as concrete: personal data about other people, material that belongs to a client or employer, anything under NDA, credentials, and figures that identify a specific deal.

A threshold you apply (“we do not discount below 20%”) is fine; the name of the client it came from is not.

The steps

1. Connect avva Studio to your own assistant

Studio is itself an MCP. You add it to Claude or ChatGPT the way you would add any other connector. From then on, your assistant does the reading and drafting, on your side.

2. Point your assistant at your material

It first asks what is off limits. Then it goes through what you give it and drafts candidate decisions in the shape above. Your sources stay with your assistant; they are not sent to avva.

3. Read every record and approve what is right

You see each candidate in full before anything leaves your side. Fix the wording, drop what you would not stand behind, and supply missing reasons yourself. A plausible guess is not a record of why you decided.

4. Let your assistant build the model

From the approved decisions it writes the structure: what you weigh first, where you stop, what changes your usual answer, and what you ask before deciding. You read that back too.

5. Publish

The published model carries the decisions in general terms, and source quotes never publish. A new model starts private. When you open it to everyone, it gets a public page and an address that anyone’s assistant can connect to.

What it costs you

• Your assistant’s time. A full sweep of years of history can take an hour or more, and a noticeable share of your plan’s usage.
• Your attention. Your part is reading what it found and the draft it shows you. That reading is what makes the model yours.
• Money. Building and publishing are free during the beta. You sign in to own what you publish. Charging for access is not open yet.

What it looks like from the other side

Back to the contract. In avva’s composite studio example, a client asks for rights to everything created, including rejected concepts and internal tools. The model’s decision is to transfer delivered, paid work and keep rejected concepts and reusable tools.

After connecting the model, try two checks:

• Ask which rights you should transfer in your contract. Does the assistant separate delivered work from internal tools, cite the model, and ask about missing terms?
• Ask a question outside the model’s field. Does it name the gap, or invent the author’s position?

Read the answers yourself. The assistant speaks as itself and credits the model. It is not a measured improvement over an unconnected assistant, and it is not legal advice.

Is your expertise a good fit

It works best when:

• your field involves repeated judgment calls, not one-off facts;
• you can explain why you decided, not only what;
• other people regularly ask you, or people like you, the same kinds of questions.

Pricing, hiring, product scope, contract terms, operations, and client management all fit. Lookup knowledge, like a tax rate or an API parameter, does not need a model of anyone’s judgment.

If what you want is a chatbot that talks to your audience in your voice, that is a clone, and a different product.

Start

Open avva Studio. The first step asks only for a public name and the field the model covers, and no account is needed until you publish.