Integration
MCP for ActiveCampaign: Claude, reading your account and CRM.
You've run ActiveCampaign for years. It sends the campaigns, it runs the automations, the deals move through the pipeline. Then you go to tidy it and the scale of the sprawl lands: four hundred tags, half of them near-duplicates nobody remembers creating, a dozen automations that were switched on for one launch and never off, and lists whose real engagement you couldn't state without exporting three reports. Ask Claude for help and it gives you good advice about all of it. Generic advice. It has never seen your tags, your automations, or last quarter's open rates. An MCP for ActiveCampaign — a way to hand Claude your account's API URL and token instead of general knowledge — is what closes that gap. Claude stops describing the audit and starts running it against your real account.
What "MCP" actually means here.
MCP stands for Model Context Protocol, an open standard from Anthropic that lets Claude reach outside the chat window. Think of it as a plugin system, except the plugins don't add small features — they give Claude entirely new capabilities: tools that read your data and build real artifacts. Orbit is one such MCP, built for lifecycle marketing. Install it, connect your ActiveCampaign API URL and token, and Claude gains the ability to read your account — and, if you confirm it, write to it. Orbit is not an official ActiveCampaign product; it's an independent MCP that calls ActiveCampaign's public v3 API with the token you provide, and nothing leaves your machine except the calls to ActiveCampaign you configured. The full walk-through of what an MCP is and how it changes the work lives on the MCP for marketing page →.
What Orbit does with ActiveCampaign today.
No hand-waving. ActiveCampaign's v3 API is deep on the read side — contacts, tags, lists, automations, deals, reports all come back natively — and thinner on authoring. Where there's a limit, it's named, and we're careful to separate three different things: what ActiveCampaign's API genuinely allows, what Orbit holds back on purpose because the action is a write and its posture is read-first, and where the API itself doesn't own the surface. Orbit paces every read under ActiveCampaign's five-requests-per-second account limit, so a full audit walks the account steadily instead of tripping throttling.
Check the connection
Works todayActiveCampaign has no dedicated health endpoint, so Orbit makes one lightweight read against your account's API URL to confirm the URL-and-token pair is live before anything else runs — no guessing whether you're connected.
Read contacts, tags, and lists
Works todayEvery contact, every tag, and every list — with the counts behind each. This is the raw material for list-health sizing and for spotting the tag sprawl that ActiveCampaign accounts collect over the years.
Read your automations
Works todayYour full automation roster with each one's active or inactive state, so Claude can see the twelve half-finished journeys and the two that double up on the same people. The step-by-step graph is thinner in the API, so Orbit reasons from the roster and each automation's status rather than redrawing every branch.
Read deals and pipelines
Works todayThe CRM side natively: deals, pipelines (deal groups), and stages. Claude can look at the sales pipeline sitting next to the marketing list instead of reasoning about only one half of the account.
Pull campaign reports
Works todayOpens, clicks, bounces, and unsubscribes per campaign from the campaigns API — aggregated the way a deliverability and engagement review actually reads them.
Read custom fields
Works todayContact and deal custom fields, so Claude reasons about your real data model — the fields your automations and segments actually key off — rather than a generic contact shape.
Apply and clean up tags
Partial — named limitAdding, merging, and removing tags is a write. ActiveCampaign's API supports it cleanly, but Orbit keeps it behind the read-first line: it proposes the tag-hygiene fixes from the audit and only applies them once you confirm. Off until you ask.
Compose and update campaign HTML
Partial — named limitActiveCampaign's v3 API is read-deep but thin on campaign authoring — there's no clean public endpoint to push a finished HTML campaign the way the designer builds one. So Orbit composes the copy, generates dark-mode-safe HTML, and runs its QA gate locally; you paste the result into ActiveCampaign's editor. The canonical HTML stays in your repo.
Trigger an automation or send a campaign
Held back by designReading automations and campaigns works today. Enrolling a contact into an automation or firing a campaign is a high-consequence write Orbit holds back from by default, so sends and enrolments stay in your hands, in ActiveCampaign, on purpose. Not an API dead-end, a deliberate line.
The short version: Orbit can read your entire ActiveCampaign account — tags, automations, lists, deals, custom fields, campaign reports — and tell you what's wrong. Tag cleanup and campaign HTML it will build too, once you confirm. The one line it won't cross without you asking is firing an automation or a campaign: that stays yours.
The clean-up audit it was built for.
This is where a read-first ActiveCampaign connection earns its place. Point Orbit at your account and ask Claude to run the tidy-up an operator keeps meaning to do and never has time for — except it reads the real state instead of asking you to describe it.
- Tag hygiene. ActiveCampaign accounts collect tags the way a garage collects boxes. Orbit reads every tag and how many contacts carry it, then surfaces the duplicates, the near-duplicates (
vip,VIP,vip-customer), and the tags nobody has applied in a year — the mess that breaks the segments and automations keyed off them. - Automation sprawl.Orbit reads your full automation roster and each one's active or inactive state, so the launch flows switched on once and never off, and the two journeys that both enrol the same people, surface as a list instead of a suspicion.
- List and engagement health.Orbit sizes your lists against their unsubscribe and bounce history and reads campaign engagement over time, so a list that's decaying shows up as a trend — and it separates a dead list from a deliverability problem, which look the same from the outside but need different fixes.
None of this needs a single write. The whole audit runs on reads — and because ActiveCampaign's token can do more than that, Orbit is the thing keeping it read-only until you say otherwise.
How to connect it.
Two fields, both in one place. In ActiveCampaign, go to Settings → Developer. Copy your account's API URL and API Key, paste both into Orbit's config, and you're connected.
- API URL — your account-specific base, like
https://youraccount.api-us1.com. ActiveCampaign gives every account its own host, so Orbit needs the URL as well as the token to know which endpoint to call. - API key — one token, full access. ActiveCampaign has no read-only variant, so the read-first posture is enforced by Orbit, not the token: it defaults to reads and holds every write behind your confirmation. If your plan supports user permissions, generating the token from a limited user is a sensible extra belt.
The token is stored as a secret and never leaves your machine in plain text. That's the whole setup — no OAuth dance, no app to install on ActiveCampaign's side. Orbit paces its calls under the five-per-second account limit, so a large audit stays polite to the rest of your integrations.
What's deepest on Braze — and why we say so.
Orbit works with every major ESP, but its deepest single-platform integration is Braze. A handful of Orbit's tools are built around concepts that only exist in Braze — Canvas flows, Content Blocks, its media library — and those stay Braze-named on purpose. Faking an ActiveCampaign equivalent would just be a worse version of a thing ActiveCampaign's model doesn't have.
For ActiveCampaign, that trade barely bites: the portable work — auditing tags and automations, reading the CRM alongside the marketing list, composing templates, running the numbers — is exactly what an SMB automation-and-CRM team needs. And if you later graduate to a lifecycle-native platform, the tooling and the discipline travel with you.
The half that isn't about the API at all.
Reading and writing ActiveCampaign is the connection. The reason to bother is everything Claude does once it's connected. Orbit ships 79 lifecycle skills — structured protocols for the actual jobs: auditing an account, composing an email, laddering a win-back, scoring a subject line. Those are ESP-agnostic; they work the same whether the account underneath is ActiveCampaign or anything else.
Underneath sit 130 tools — an MJML pipeline that compiles to clean, dark-mode-safe HTML, a render-and-QA gate that catches the clipping and inbox breakage before you send, and the calculators a real test needs: sample size, holdout, replenishment timing. ActiveCampaign gives you the automations and the CRM. Orbit is the practitioner sitting next to them, reading the same screens you do.
Is this for you?
This is for the SMB marketer or operator who runs ActiveCampaign and wants a straight read on it — the person maintaining the tags, watching the automations pile up, and trying to keep the lists and the pipeline honest. If that's your week, Orbit hands you a Claude that reads the real state through a token you control. It's a weaker fit if you want a hands-off tool that runs the program while you watch a dashboard. Orbit doesn't run your program, and it won't fire your automations. You do. It just gives you a Claude that works like a lifecycle operator instead of a search engine — and a straight answer about what your ESP can and can't do, which is rarer than it should be.
Try it.
Orbit is free — every skill and tool included, no seats and no subscription. Paste your ActiveCampaign API URL and token and Claude goes from advisor to account audit the same afternoon.
Run a different ESP?
The same honest treatment, per platform:
Frequently asked.
What is an MCP for ActiveCampaign?
An MCP — Model Context Protocol, an open standard from Anthropic — gives Claude real tools instead of general knowledge. Connected to ActiveCampaign through Orbit with your own account API URL and token, Claude can read your contacts, tags, lists, automations, deals, and campaign reports — rather than describing what you should do and leaving the doing to you. It is not an official ActiveCampaign product; it is an independent MCP that calls ActiveCampaign's public v3 API with the token you provide.
Does ActiveCampaign have a read-only API key?
The honest answer is no. ActiveCampaign issues one API token per account, and it carries full access; there is no scoped read-only key the way some platforms offer. So the read-first posture here is enforced by Orbit, not by the token: it defaults to reads, runs the entire audit without touching a thing, and holds every write — applying tags, composing a campaign, enrolling a contact — behind an explicit confirmation from you. The token can do more than Orbit will unless you ask.
What can Orbit read for an audit?
The pieces a real audit is made of. Contacts, tags, and lists come back with the counts behind each, so Claude can size list health and spot the tag sprawl. Your automations arrive with their active or inactive state, which is how the half-finished journeys and the overlaps surface as a list. From the CRM side come deals, pipelines, and stages, plus your custom fields, so Claude reasons about your real data model. And campaign reports land too — opens, clicks, bounces, unsubscribes — for the engagement numbers a review actually needs.
Can Orbit build ActiveCampaign campaigns or templates?
Partly, and the constraint is ActiveCampaign's, not Orbit's. The v3 API is read-deep but thin on campaign authoring — there's no clean public endpoint to push a finished HTML campaign the way the visual designer builds one. So Orbit composes the copy, generates dark-mode-safe HTML, and runs its own QA gate locally; you paste the result into ActiveCampaign's editor. The canonical HTML lives in your repo and ActiveCampaign holds the derived copy — which is the honest split when an API doesn't own the authoring surface.
How does Orbit handle ActiveCampaign's API rate limit?
ActiveCampaign caps the v3 API at five requests per second per account, shared across everything hitting it. Orbit paces its reads to stay under that ceiling, so a full tag-and-automation audit walks the account steadily instead of hammering it and tripping throttling. If your account is busy with other integrations on the same limit, an audit simply takes a little longer — it doesn't fail.
Is ActiveCampaign the right home for a serious lifecycle program?
For an SMB that wants marketing automation and a light CRM in one place, ActiveCampaign is a strong home — its automations, tagging model, and deal pipelines cover a lot of real activation-to-retention work, and Orbit gives you a practitioner's Claude on top. Where it strains is deep, branching, behaviour-driven journeys and true incrementality testing across a large audience; if that's the week you're living in, a lifecycle-native platform like Braze is the graduation. Orbit works with both, deepest on Braze — so the tooling and the discipline travel with you if you move.