Failed deploy
A developer sees the preview is stale and asks why. Memtro reads the site's recent deploys, finds the latest in an error state, and returns its branch, commit, error message and timings beside the last deploy that succeeded.
Why the last Netlify deploy failed, what went live today, and where DNS points.
Connect Netlify with a personal access token and Memtro reads sites with URL, domain and last published deploy, deploys with state, branch, commit, error message and timings, and DNS records. It reads on demand and there is no hourly sync. When you ask, and once an administrator has granted the action by name, it can start a build and deploy, publish an earlier deploy, roll production back, cancel, lock or permanently delete a deploy, release a lock, and take a site offline or bring it back. Most change the live site for every visitor, and builds use build minutes.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Netlify tool, reads what it needs, and answers with the source cited.
These tools change something in Netlify. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Netlify for you. Each event can start a job, with the event as its input. Netlify signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Netlify is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Why did the last deploy of the marketing site fail?
What went live on Netlify today?
Which branch and commit is the docs site's production deploy built from?
Where does the www record for acme.com point?
Roll the marketing site back to its previous deploy
A developer sees the preview is stale and asks why. Memtro reads the site's recent deploys, finds the latest in an error state, and returns its branch, commit, error message and timings beside the last deploy that succeeded.
Ten minutes after a release, Tom Becker reports that checkout on the Acme site is broken and asks Memtro to roll it back. Memtro rolls production back to the previous deploy, every visitor gets the earlier version, and the broken deploy stays listed for the developers to inspect.
The teams that lean on Netlify most, a question each of them asks, and what they connect beside it.
A record in Netlify is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
At app.netlify.com → User settings → Applications → Personal access tokens, choose New access token and set an expiration
Tick SAML team access if your team signs in with SAML. Copy the token. It has your access to every team you belong to, and resetting your password invalidates it
In Memtro open Connections → Netlify, paste the Personal access token and connect. An administrator then grants deploys and rollbacks by name
Ask why the last production deploy of your main site failed
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Netlify tools are the same everywhere.
Only when you ask, and only what it has been granted: start a build and deploy of a site, to production unless a branch or draft is named; publish an earlier deploy of a site again; roll a site's production back to its previous deploy; cancel a deploy that is still building; lock a deploy so later deploys are built but not published, publishing it first if it is not live; unlock a site's locked deploy so new deploys publish again; delete a deploy; take a site offline for every visitor; bring a disabled site back online. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Personal access token. At app.netlify.com → User settings → Applications → Personal access tokens, choose New access token and set an expiration.
Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Netlify for you. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time