Dunedin sits in a regional context that genuinely changes the build. Connectivity assumptions, the rhythm of the working week, the proximity of your team to your customers – none of those are details our default MCP integrations template would catch.
Otago · Applied AI
MCP integrations designed around the way a Dunedin team actually runs.
What MCP integrations actually does
Wire Claude, ChatGPT, or Gemini directly into your tools with the Model Context Protocol. Your team uses AI in their existing inbox, CRM, or chat – with your data, your permissions, your guardrails.
- 01 Custom MCP servers for your CRM, ERP, or in-house tools
- 02 Permission-aware so AI only sees what each user can
- 03 Tool-call audit log for compliance
- 04 Works with Claude Desktop, ChatGPT, Cursor, and more
Built on: MCP Claude TypeScript Vercel
Without Kiwi Dynamics
With Kiwi Dynamics
Otago
The pattern across Dunedin engagements we've shipped.
- Dunedin pairs a strong university research culture with practical southern businesses. AI here means proven tools, not hype.
- Education, health, tech, and a tourism shoulder season that hits hard. AI helps Dunedin teams smooth the peaks and protect the people.
We work with teams across Dunedin: CBD · North Dunedin · South Dunedin · Mosgiel · Port Chalmers · Green Island.
Talk to us about this →
How we build MCP integrations for a Dunedin team.
We scope narrow, ship a working pilot, then harden it into production. The first slice is the highest-leverage workflow for your Dunedin business, so value lands before the build is finished. Connect Claude to your stack.
Talk to usThe outcome for Dunedin teams
Existing AI tools become 10x more useful with real business context. For Dunedin teams, that almost always shows up as fewer interruptions and a calmer week, not a dashboard chart.
Not your typical AI agency.
Honest about what AI can and cannot do
Ships the one workflow that pays for itself
Hours given back, never the size of the invoice
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
Questions
FAQ
How fast could we have MCP integrations in production?
Eight to ten weeks for most Dunedin businesses. Faster if your data is in good shape and slower if we're untangling a legacy integration first. We'll give you a realistic number on the scoping call rather than the optimistic one.
What's the smallest engagement you'd take on?
A two-week paid discovery for Dunedin businesses that aren't sure whether the build is worth doing at all. You get a one-page write-up of what we'd build, what we'd skip, and what it would cost. About 30% of those discoveries end with us recommending you don't proceed.
Anyone else in this space using MCP integrations?
Plenty. Existing AI tools become 10x more useful with real business context. The interesting question is rarely "does it work" – it's "is your team ready to use the output." That's what we'd scope on the call.
What if our Dunedin doesn't have any data ready?
Most don't. Getting the data into shape – ingestion, cleaning, the lightweight contracts you need before any model is useful – is part of the engagement. For MCP integrations specifically, we typically run that work on MCP, Claude, TypeScript, Vercel and assume messy starting conditions from day one.
One reply, one direction.
We don't run sequences or follow-up automation. One useful answer, one decision on your side.
Get in touch
Talk to us about this
Tell us what you're trying to do and we'll reply with how we'd build it — no obligation.