A pre-release check
Sarah Chen, content manager at BigCo, asked which blog posts had unpublished changes. Memtro listed three records with status updated and when each was last changed, with a preview of what had changed in each.
DatoCMS + Memtro
Which DatoCMS records have unpublished changes, and what changed this week?
DatoCMS connects Memtro to your project's content. It reads the models, then the records of any model, each with its status as draft, updated or published, its dates and a preview of each field. It opens one record in full and reads the media library. An hourly sync keeps changed records in memory. When asked and once an administrator has granted the action by name, it can create, update, duplicate, publish, schedule or unpublish records, and edit media metadata. Publishing puts content live on your site and can start your builds. Deleting a record or a media asset is permanent.
In Memtro
What you can do with DatoCMS in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right DatoCMS tool, reads what it needs, and answers with the source cited.
What it does
- 01Lists the project's models, and records with model, title, status, dates and a preview of each field.
- 02Filters records by model, words, status or changed since a date.
- 03Opens one record with every field, as the current draft or the published version, each field cut to 1,500 characters.
- 04Lists the media library with file name, type, size, dimensions, alt, title, author, copyright and tags.
- 05When asked and granted, creates, updates or duplicates records as drafts, and publishes, schedules or unpublishes them, up to 200 at once. Publishing puts them live and fires any publish webhooks or builds.
- 06When asked and granted, edits a media asset's alt text, title, author, copyright or tags, and permanently deletes a record or a media asset.
Acts when asked
When you ask it to
These tools change something in DatoCMS. 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.
- 01Create a DatoCMS record (as a draft)
- 02Update a DatoCMS record's fields
- 03Publish a DatoCMS record (live on the site)
- 04Unpublish a DatoCMS record (taken off the site)
- 05Delete a DatoCMS record (permanent)
- 06Duplicate a DatoCMS record
- 07Schedule a DatoCMS record to publish
- 08Schedule a DatoCMS record to unpublish
- 09Publish up to 200 named DatoCMS records at once
- 10Edit a DatoCMS media asset's metadata
- 11Delete a DatoCMS media asset (permanent)
Events
When it happens
Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with DatoCMS for you. Each event can start a job, with the event as its input. DatoCMS sends a secret with every delivery, and one without it is refused.
Events and webhooks- 01Record created
- 02Record updated
- 03Record deleted
- 04Record published
- 05Record unpublished
- 06Model created
- 07Model updated
- 08Model deleted
- 09Asset created
- 10Asset updated
- 11Asset deleted
- 12Build trigger deploy started
- 13Build trigger deploy succeeded
- 14Build trigger deploy failed
- 15Environment promoted
- 16Maintenance mode changed
- 17SSO user created
- 18Cache tags invalidated
In practice
Ask it like you would a colleague
Once DatoCMS 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.
DatoCMS + Memtro
Which blog posts have unpublished changes?
What changed in the product catalogue this week?
Which images in the media library have no alt text?
Show me the published version of record 81234.
Publish the three blog posts Sarah updated today.
Publishing for the newsletter
Dan Fletcher, product manager at Acme Ltd, asked Memtro to publish the three updated posts before the newsletter went out. Memtro published the named records, which went live on the site and started the project's publish build in DatoCMS.
Teams
Where it fits
The teams that lean on DatoCMS most, a question each of them asks, and what they connect beside it.
- MarketingSpend, leads and reputation in one conversationMarketing lead, Performance marketer, Content and SEO, Brand and community“How did last week's LinkedIn and Google campaigns do, and which leads reached the pipeline?”Used alongside Google Ads, Meta Ads, HubSpot, Google Analytics 4, Brevo and 7 more.
- ProductHear what customers actually ask forProduct manager, Researcher, Designer, Head of product“Which customers asked for SSO this quarter, and what is their combined ARR?”Used alongside Help Scout, HubSpot, Linear, Jira, Slack and 6 more.
- OperationsMonitors and digests that run themselvesOperations lead, Analyst, Team manager, Administrator“List my jobs”Used alongside Help Scout, Stripe, Xero, Postgres, ShipEngine and 8 more.
Better together
Works with
A record in DatoCMS 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.
- Marketing automationDatoCMS with ActiveCampaignContacts, campaigns and automations from ActiveCampaign.
- Marketing automationDatoCMS with BrevoEmail and SMS campaign results from Brevo.
- Marketing automationDatoCMS with Customer.ioCampaign metrics and customer journeys from Customer.io.
- AnalyticsDatoCMS with Google Analytics 4Ask your traffic questions in plain English and get the numbers back.
- AnalyticsDatoCMS with Plausible AnalyticsAsk about your website traffic in plain English.
- AnalyticsDatoCMS with UmamiAsk about your website traffic in plain English, without sending anybody to a dashboard.
- Documents and wikisDatoCMS with NotionSearch pages and query databases, and write to them when you ask.
- Documents and wikisDatoCMS with Google DriveSearch Drive and read Docs, Sheets and Slides as text, and write a Doc when you ask.
- Documents and wikisDatoCMS with ConfluenceSearch and read wiki pages, and write them when you ask.
Also in Content and web
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- Ahrefs
- WordPress
- Webflow
- Typeform
- Eventbrite
- Contentful
- Ghost
- Open law
- Semrush
- treg
- UK Postcode Information
- Web scrape
- Web search
Jotform- Sanity
- Tally
DataForSEO
Moz API- SE Ranking
- Ideal Postcodes
- Ticket Tailor
- Directus
- Strapi
- Storyblok
- Prismic
- Fillout
Hygraph- Wix
Paperform- ButterCMS
- Cloudinary
- Contentstack
- DNSimple
- Gandi
- Joomla
Kajabi
Kontent.ai- Mux
- Porkbun
Teachable- Uploadcare
- Vimeo
Wufoo
Setup
How to connect
Connect withAPI token
- 1
In DatoCMS, go to your project → Project settings → API tokens and create a new API token, not the built-in full-access one.
- 2
Turn on Access the Content Management API, give it a role that can read records and the media library, plus only the create, edit, publish or delete permissions for the actions you will grant, and copy the token.
- 3
In Memtro, open Connections → DatoCMS and paste it into API token, filling Environment only for a sandbox.
- 4
Ask: which blog posts have unpublished changes?
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The DatoCMS tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in DatoCMS?+
Only when you ask, and only what it has been granted: create a DatoCMS record (as a draft); update a DatoCMS record's fields; publish a DatoCMS record (live on the site); unpublish a DatoCMS record (taken off the site); delete a DatoCMS record (permanent); duplicate a DatoCMS record; schedule a DatoCMS record to publish; schedule a DatoCMS record to unpublish; publish up to 200 named DatoCMS records at once; edit a DatoCMS media asset's metadata; delete a DatoCMS media asset (permanent). 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.
Who can use a DatoCMS connection?+
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.
Does Memtro store my DatoCMS data?+
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. An hourly sync anchors recently changed DatoCMS records into memory as entities.
How do I connect DatoCMS?+
API token. In DatoCMS, go to your project → Project settings → API tokens and create a new API token, not the built-in full-access one.
Can DatoCMS start a job?+
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 DatoCMS 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.
Connect DatoCMS in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.