Resources · Make integration

Anthropic Claude Make integrationAutomate Anthropic Claude with Make.

What can Claude do inside your automations when nobody is typing in a chat window? The Anthropic Claude Make integration gives you 2 action modules: one sends Claude a prompt, the other calls the API directly. This guide shows where each fits and walks you through a first scenario.

Try the Anthropic Claude integration on MakeSee the 2 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What does the Anthropic Claude Make integration actually do?

The Anthropic Claude Make integration lets a Make scenario (the automation you build, a chain of steps) hand text to Claude and pass the result to the next step. Something happens in another app, Claude gets a prompt built from that data, and what comes back continues down the chain without anyone copying and pasting.

Draft replies for a support queue. A new ticket lands in your helpdesk, Create a Prompt passes its text to Claude along with your instructions, and the draft goes back to the ticket for an agent to review. The human still decides; the blank page is gone.

Qualify new leads before sales opens them. A form submission starts the scenario, Claude reads the answers and writes a short note for your sales team, and that note travels to the CRM record. Your reps open a lead and already know what it is about.

Reach what the listed modules skip. Anthropic Claude has only two modules in Make. When you need an endpoint neither of them covers, Make an API Call uses the same connection to reach any part of the Anthropic API.

One thing Make does not offer here: a trigger. Claude never starts a scenario on its own, so another app or Make's own schedule has to kick things off. If you would rather build this in n8n, the Anthropic Claude n8n integration covers the node, and n8n vs Make compares both tools. New to Make overall? The Make training starts from zero.

Connect

How do you connect Anthropic Claude to Make?

  1. 01

    Add a Claude module

    In your scenario, click the + and search for Anthropic Claude. Pick Create a Prompt, then click Create a connection. A connection is your Anthropic account linked to Make once and reused by every Claude module afterwards.

  2. 02

    Name it and authorize

    Give the connection a name if you like, something that tells you which account or project it belongs to. Then follow what the window asks for: either authorize Make on Anthropic's page, or paste the key Anthropic gives you.

  3. 03

    Save and reuse

    Click Save. The connection now appears in a dropdown on both Claude modules, so the next time you add one to any scenario, you just select it instead of starting over.

First scenario

Your first scenario with Anthropic Claude

GoalWhen a new entry arrives in another app, Make sends it to Claude with Create a Prompt and hands the result to the rest of the scenario.

  1. 01

    Start from the app that holds the data

    On the Scenarios page, create a new scenario and click the +. Since Claude has no trigger, pick the module of the app where your text shows up: a form tool, a helpdesk, a spreadsheet.

  2. 02

    Add Create a Prompt

    Click the + on the right of that first module, search for Anthropic Claude and choose Create a Prompt. Select the connection you saved earlier, or create it now.

  3. 03

    Write the messages

    Build the list of messages Claude will read. Type your instruction, then map the fields from the first module into it, so every run carries the real text of that entry instead of a fixed example.

  4. 04

    Test with Run once

    Click Run once to run the scenario one time. Open the bubble above each module to read the bundles it received, one bundle being one item passing between modules. That shows you exactly what Claude returned.

  5. 05

    Schedule and switch on

    Set the schedule on the first module (every 15 minutes by default on a new scenario), then turn the scenario on. Each module run on each bundle counts as one operation on your Make plan.

Modules

What the Anthropic Claude modules do

Anthropic Claude gives you 2 modules. For each one: what it does for you, when to reach for it, and what to watch out for.

Anthropic Claude1

Create a Prompt

Action

In Make“Creates a new prompt based on a structured list of input messages.”

A prompt is simply the instruction you give Claude, the AI model that reads your text and writes back. Here you build it as a list of messages: your instruction, then data mapped from earlier modules. Claude's reply moves on to the next step.

When to use it
any time a scenario needs Claude to read, rewrite or sort text arriving from another app.
Watch out
click Run once and open the output bundle before mapping it further, to find the value holding the reply.
Anthropic Claude2

Make an API Call

Action

In Make“Performs an arbitrary authorized API call.”

Your fallback. It sends any authorized request to the Anthropic API through the connection you already set up, and you describe that request yourself. Useful when the one prompt module is not enough.

When to use it
when Create a Prompt does not cover the endpoint or the option your process depends on.
Watch out
you write the whole request yourself, so keep the Anthropic API reference open while you set it up.
Need help

Need help automating Anthropic Claude with Make?

A person reads every message.

FAQ

Anthropic Claude and Make: common questions

01Is the Anthropic Claude Make integration free?
Yes, on the Make side. Anthropic Claude is a standard app, so its modules are available from the Free plan up. The Free plan caps you at 2 active scenarios, a minimum of 15 minutes between scheduled runs, 5 minutes per execution, files up to 5 MB and 512 MB of data transfer. Paid plans drop the interval to 1 minute, remove the cap on active scenarios and allow 40 minutes per execution. Usage is counted in operations, one per module run on each bundle. Whatever Anthropic bills on its own side is a separate matter this page does not cover.
02What do you need to connect Anthropic Claude to Make?
An Anthropic account and a Make account. The Make documentation lists no extra prerequisite for this app. You add a Claude module to a scenario, click Create a connection, optionally name it, then either authorize Make on Anthropic's page or paste the key Anthropic provides, depending on what the connection window asks for. Click Save and the connection is shared by both Claude modules in every scenario you build afterwards, so you only go through this once per account.
03Does Anthropic Claude start Make scenarios in real time?
Not from Claude itself, because the app has no trigger module in Make. Claude only acts when a scenario reaches it. To get things moving, start the scenario with a trigger from another app, such as a form or helpdesk, and place Create a Prompt after it. If that app offers an instant trigger, it calls Make through a webhook as soon as something happens. Otherwise, the scenario follows its schedule, every 15 minutes by default, or 1 minute at the lowest on a paid plan.
04What if an Anthropic Claude module is missing in Make?
Use Make an API Call. With only two modules listed, Create a Prompt handles the common job of sending Claude a prompt, and anything else in the Anthropic API goes through Make an API Call, reusing the connection you already created. You write the request yourself, so keep the Anthropic API reference at hand. The Make documentation lists no numeric limits for this app, so there is no specific cap to plan around beyond your own Make plan.
05Make or n8n for Anthropic Claude?
It depends on where the rest of your processes already live. Anthropic Claude exists in both tools: in Make as the two modules described here, and in n8n as a node with its own page on this site. If your other apps are already wired into Make scenarios, adding Claude there keeps everything in one place. If your team works in n8n, the node is where you would add it. Either way, the choice is about your tooling, not about Claude.
Same platform

Other docs you might need on this stack.

Browse all integrations