Finding the runbook
A new engineer asks where the database restore steps are written down. Memtro searches Nuclino, finds the Restore runbook page in the Engineering workspace, summarises its steps and says Dan Fletcher last updated it in September.
Ask where something is documented in your Nuclino wiki, and what the page says.
Connect Nuclino with an API key and Memtro reads your teams and workspaces, searches the pages and collections in them by full text, and reads a page as Markdown with who last updated it. It sees only the workspaces the key's user can see. It reads on demand and there is no hourly sync. When asked, and once an administrator has granted the action by name, it can create, rename, rewrite or move pages and collections, edit lines of a page, put one in the trash, restore an earlier version, and attach a file.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Nuclino tool, reads what it needs, and answers with the source cited.
These tools change something in Nuclino. 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.
Once Nuclino 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.
Where is our onboarding checklist documented?
What does the wiki say about expense approvals?
Who last updated the release process page?
Create a page called Acme kick-off notes in the Clients workspace
Move the old pricing page to the trash
A new engineer asks where the database restore steps are written down. Memtro searches Nuclino, finds the Restore runbook page in the Engineering workspace, summarises its steps and says Dan Fletcher last updated it in September.
Priya Nair notices the restore runbook names an old backup bucket and asks Memtro to correct that line. Memtro reads the page, changes only the line with the bucket name, and Nuclino refuses the edit if someone changed the page in between. The rest of the page stays as it was, and the old text is kept in version history.
The teams that lean on Nuclino most, a question each of them asks, and what they connect beside it.
A record in Nuclino 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.
Nuclino may limit the API to paid plans. In Nuclino open your avatar → Settings → API keys, create an API key and copy it
The key has your access: Memtro sees only the workspaces you can see, and anything it creates or changes is done as you
In Memtro open Connections → Nuclino, paste the API key and connect
Ask where the deployment checklist is documented
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Nuclino tools are the same everywhere.
Only when you ask, and only what it has been granted: create a page (or a collection) in a workspace or collection; rename a page or collection, replace its Markdown, or set its field values; edit lines of a page's Markdown, checked against the version last read; move a page or collection to another collection or workspace; move a page or collection to the workspace trash; restore a page's content to an earlier version; attach a file to a page from a public URL. 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.
API key. Nuclino may limit the API to paid plans. In Nuclino open your avatar → Settings → API keys, create an API key and copy it.
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