How each beehiiv post did and who reads it, remembered once the numbers settle.
Connect beehiiv with an API key and Memtro reads subscriber totals and average rates, posts with opens, clicks and unsubscribes, a post's text and top links, subscribers with their engagement, segments and automations. Every hour it writes each post into memory once it is two days old. When you ask, and once an administrator has granted the action by name, it can draft and edit posts, send test copies, publish a post to subscribers, manage subscribers and automations. A published post emails readers outside the company and cannot be recalled, and deleting a subscriber is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right beehiiv tool, reads what it needs, and answers with the source cited.
These tools change something in beehiiv. 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 beehiiv for you. Each event can start a job, with the event as its input. beehiiv signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce beehiiv 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.
How did last Thursday's post do compared with the four before it?
Which links did readers click most in the 'October roundup' post?
Is priya@marlowe.studio subscribed, and does she open our emails?
How many premium subscribers do we have and what is our average open rate?
Draft a post titled 'November roundup' from these notes and send me a test
On Friday the editor asks how the week's issue landed. Memtro returns recipients, open and click rates, unsubscribes and web views, the three most-clicked links, and sets them against the publication's averages so a drop is obvious.
Hannah Cole, editor at Northwind's newsletter, pastes her notes and asks Memtro to draft the November roundup and send her a test. Memtro creates the draft in beehiiv and test-sends it to Hannah alone. Nothing reaches subscribers until she asks for it to be published.
The teams that lean on beehiiv most, a question each of them asks, and what they connect beside it.
A record in beehiiv 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.
ActiveCampaign
Klaviyo
MailerLite
GetResponse
Instantly
lemlist
Drip
Omnisend
Mailjet
Moosend
Smartlead
Iterable
Dotdigital
Flodesk
LoyaltyLion
Benchmark Email
Braze
Sender
Rewardful
Mailshake
SurveySparrow
RetentlyIn beehiiv open Settings → Integrations → API Keys and create an API key. Copy it straight away, it is shown once, and it reaches every publication in the workspace unless restricted when created
If the key reaches more than one publication, note the Publication ID under Settings → Integrations → API (API V2). With one publication leave it blank
In Memtro open Connections → beehiiv, paste the API key, and the Publication id if needed, and connect
Ask how last week's post did. beehiiv allows 30 requests a minute on Free, 180 on Lite, 500 on Pro and 800 on Enterprise
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The beehiiv tools are the same everywhere.
Only when you ask, and only what it has been granted: draft a newsletter post; edit a draft or scheduled post's title, subtitle, content, tags or send time; send a test copy of a post to named addresses; publish a draft post to the audience now, or schedule it; delete a draft post, or archive a published one; subscribe an email address, optionally with a welcome email; change a subscriber's email, custom fields or lists, or unsubscribe them; delete a subscriber and all their data (permanent); add a subscriber to an automation, which sends them its emails; delete a segment (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 beehiiv records into memory as entities.
API key. In beehiiv open Settings → Integrations → API Keys and create an API key. Copy it straight away, it is shown once, and it reaches every publication in the workspace unless restricted when created.
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 beehiiv 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