> For the complete documentation index, see [llms.txt](https://docs.doma.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.doma.xyz/agentic-commerce/mcp-server/examples.md).

# Examples

What the server feels like in use. You don't name tools or pass parameters — you ask, and the agent picks the tools and chains them.

## Research a name

> Is `spark.ai` tokenized on Doma? If it is, tell me who owns it, when it expires, and whether anyone has an open offer on it.

One lookup answers all of it — ownership, expiry, registrar, nameservers, and open offer count come back together.

## Find something to register

> I want a short two-word `.ai` domain for an AI recruiting tool. Check availability for ten candidates and tell me the cheapest three across registrars.

The agent generates the candidates itself, checks live availability, and prices the survivors per registrar — the "generate candidates" half is the part an API can't do for you.

## Shop the marketplace with a budget

> Show me every active Doma listing under $500, and for the three cheapest tell me the total I'd actually pay including fees and royalties.

Quoting surfaces the real number — fees and royalties — not the sticker price.

## Buy one

> Buy the cheapest active listing for `example.com`, but only if the all-in total is under $200. Quote it first and tell me the number before you buy.

Quote, check against the ceiling, then one atomic gasless purchase — inside the budget you set at [authorization](/agentic-commerce/mcp-server/authorization.md).

## Trade a fractional token

> Which Doma launchpad tokens are still on their bonding curve and opened for trading this week? Give me 24h price change for each, then swap $25 of USDC into whichever is down the most.

The agent doesn't need to know bonding curve vs. Uniswap pool — routing is the tool's job.

## Rest a limit order

> If `example.ai` fractional tokens drop to $0.40, buy $50 worth. Approve whatever's needed and leave the order resting.

The agent approves the DomaOrderRouter to spend that much USDC, then places a limit order that fills automatically off-session when the price hits — no need to stay connected. Ask *"what limit orders do I have open?"* to check on it, or *"cancel my `example.ai` order"* to pull it. The router approval, not your USD budget, bounds what these orders can spend — see [Authorization & Spend Controls](/agentic-commerce/mcp-server/authorization.md#limit-orders-a-separate-authority-track).

## Audit a portfolio

> Look at the balances in my wallet, and for every fractional domain token I hold tell me what it's worth now and whether it's up or down over 24 hours.

## Check the DNS on a domain you own

> What DNS records are set on `mysite.com` right now? Show me the A and MX records and tell me which nameservers it's delegated to.

## Stay in control

> How much spend budget does my Doma agent have left?

> Lower my cap to $20.

> Revoke my Doma agent session.

Supervising the agent is the same conversation as directing it — see [Authorization & Spend Controls](/agentic-commerce/mcp-server/authorization.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.doma.xyz/agentic-commerce/mcp-server/examples.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.