What changed in our Hygraph blog posts this week?
Hygraph connects Memtro to your headless content. It learns the project's content models by introspection, such as Post, Product or Author, lists the entries of any model, newest change first, with created, updated and published dates and short previews of their fields, and lists assets with file name, type, size and URL. It reads PUBLISHED or DRAFT content. When asked, and once an administrator has granted the action by name, it can create and edit draft entries, publish or unpublish entries and assets, which changes what the website shows, add assets from a URL, and permanently delete entries and assets.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Hygraph tool, reads what it needs, and answers with the source cited.
These tools change something in Hygraph. 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, then add the address it shows as a webhook in Hygraph, choosing the same kinds; the tab shows Hygraph's own steps. Each event can start a job, with the event as its input. Hygraph signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Hygraph 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.
Hygraph + MemtroWhat changed in our Hygraph blog posts this week?
Which content models does our Hygraph project have?
Show the draft versions of our product entries changed since Monday.
When was the pricing page entry last published?
Publish the draft of the spring launch post
Maya Okafor, content lead at Northwind, asked what had changed in the blog this week. Memtro listed Post entries changed since Monday, with updated and published dates and a preview of each title. Two had been updated after they were last published, which she raised at stand-up.
Tom Reilly, web developer at Acme Ltd, asked Memtro to fix a wrong price in the pricing page entry and publish it. Memtro changed the field in the entry's draft, then published it to PUBLISHED, and the website showed the corrected price.
The teams that lean on Hygraph most, a question each of them asks, and what they connect beside it.
A record in Hygraph 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.
Jotform
DataForSEO
Moz API
Paperform
Kajabi
Kontent.ai
Teachable
WufooIn Hygraph, open Project Settings → Access → Endpoints and copy the Content API URL.
Under Permanent Auth Tokens, add a token named Memtro with PUBLISHED as the default stage. Choose Initialize defaults or add Read permission, and add Create, Update, Delete and Publish on the models concerned only if entry or asset actions will be granted. Copy it.
In Memtro, open Connections → Hygraph and paste Content API endpoint and Permanent Auth Token.
Ask: what changed in our Hygraph blog posts this week?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Hygraph tools are the same everywhere.
Only when you ask, and only what it has been granted: create a draft entry in a model; update fields of one entry (the draft, published content changes when it is published); publish one entry to a content stage (readers of that stage see it); unpublish one entry from a content stage (readers lose it); delete one entry (permanent); create an asset from a public URL; publish one asset; unpublish one asset; delete one 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.
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. An hourly sync anchors recently changed Hygraph records into memory as entities.
Content API endpoint and Permanent Auth Token. In Hygraph, open Project Settings → Access → Endpoints and copy the Content API URL.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Hygraph, choosing the same kinds; the tab shows Hygraph's own steps. 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
