Urbanise Strata MCP Server · Release Notes

What's new in the
Urbanise Strata MCP Server.

We're improving the Urbanise Strata MCP Server all the time — more of your portfolio a question away, tighter controls on the things that move money, and fixes that make everyday work smoother. Here's what's changed, newest first.

Security New Improved Fixed
v1.0.026 July 2026

Your strata portfolio, in conversation

New

89 things you can ask for, across the whole portfolio. Plans, lots, owners and committees; levy summaries, lot ledgers and arrears; budgets, funds, investments and disbursements; suppliers, preferred and blacklisted lists, insurance and work orders; tenants, common property and rentals; tasks, invoices, receipts and payment runs. Everything in the User Guide, in plain language.

New

Every Urbanise operation is covered, without 139 near-identical actions. Urbanise exposes most operations two or three times over — by plan number, by external reference, sometimes by property id. Those are collapsed into one action each, so your assistant picks the right one instead of guessing between three that look the same. All 139 operations are reachable through 89 actions.

New

Connect from any compliant AI client, unaided. The server runs its own secure sign-in, so a client like the claude.ai connector completes the whole connection on its own — no token pasted in out of band, and the connection survives its access lapsing rather than dropping you mid-session. Services that run unattended can still authenticate directly with a client id and secret.

Security

Two independent gates on anything that writes. A connection holds either read access or read-and-write access, and separately, a whole deployment can be switched to read-only without touching a single credential. Either one alone stops every change; both have to be open for anything to be written.

Security

A read-only connection can't even see the write actions. They're filtered out of the list your assistant reads, so it never offers something it isn't permitted to do — and never has to be trusted not to try. Verified on the staging deployment: 45 actions visible, and a write action refused outright when called directly anyway.

Security

Eight actions are flagged as irreversible. Deleting an accrual, removing an owner's associated contact, deleting a user, and the five payment-run state changes are annotated so your assistant requires explicit human confirmation before any of them. Money movements — receipting levy and invoice payments, dispatching a batch — can't be reversed through the assistant either, and say so up front.

Security

It can only ever reach your own portfolio. The strata client the server acts on comes from its configuration and is never something a request can supply. A test enforces that no action exposes it, so there's no path — accidental or otherwise — to another management company's data.

Security

Only the actions you need. The server is organised into 16 groups, and any group can be switched off for a deployment. A manager with no need for payment-batch handling or user administration has those removed entirely, rather than relying on nobody calling them.

Improved

Honest about what it doesn't know. Urbanise's portfolio-wide owner-name search doesn't match the owner names it returns — any realistic surname comes back empty. An empty result there is now returned with an explicit advisory rather than as a bare "no results", so your assistant redirects you to a building-scoped search instead of reporting an owner as absent. Owner lookup within a plan matches names correctly.

Fixed

The health check now proves it can actually read your data. The readiness check previously only confirmed the credentials were present, so it could report healthy on a revoked or wrong-environment credential — and a deployment that couldn't make a single successful Urbanise call would have passed its release gate. It now performs a real read against your tenant before reporting ready.

Improved

Failures come back as advice, not stack traces. When Urbanise refuses something, the reason is translated into something you can act on. Internal detail is logged on the server and never returned. Rate limits are honoured automatically, and long lists come back paged with an honest indication of whether there's more.

Security

Credentials never sit in the open. Secrets live in a managed vault and are read with a managed identity — nothing in a repository, nothing in plain configuration. Passwords, client secrets and access tokens are never written to a log, and a test enforces it. Rotating one signing key immediately invalidates every outstanding connection.

Improved

Early access is open. This first version is deployed and connected, running read-only while write operations are verified against a live tenant. If you'd like your organisation's server, register your interest and we'll be in touch.