How to move from Make to FlowRunner

This guide moves your Make scenarios to FlowRunner without rebuilding each one by hand. FlowRunner Prompt to Flow connects to the AI tool you already use, reads a scenario’s exported blueprint, and builds the same workflow as a FlowRunner flow in your workspace.

You convert one scenario at a time. What’s left for you is reconnecting your accounts, setting the schedule, and testing.

1. Export your scenarios from Make

Make exports one scenario per file, as a JSON blueprint:

1. Go to Scenarios and open the scenario.
2. Click the three dots in the upper right of the Scenario Builder.
3. Choose Export blueprint. Make downloads a .json file named after the scenario.

Copy blueprint to clipboard in the same menu gives you the same JSON as text, which you can paste straight into the chat. Make’s help page names no plan limit for either.

According to Make, a blueprint holds the scenario’s modules, their settings, and the values you mapped between them. Two things don’t come with it: your connections, and the scenario’s schedule. Make’s help page doesn’t say whether webhooks, data stores, data structures, or scenario settings are included, so plan as if they aren’t.

Before you leave each scenario:

• Write down the schedule, or note which webhook or app starts it.
• Note any data stores the scenario reads or writes, and copy out their records if you need them.
• Save a few real inputs from the scenario’s recent runs, so you have something to test the new flow with.

Keep the blueprints, too. Make’s own import takes blueprints under 2 MB, so the files are a backup you can bring back into Make.

If you have a lot of scenarios, Make’s API returns any scenario’s blueprint (GET /scenarios/{scenarioId}/blueprint, with an API token), so a short script can save them all.

2. Connect FlowRunner Prompt to Flow to your AI tool

FlowRunner Prompt to Flow is an MCP server you add to the AI tool you already use. You connect it once and sign in with your FlowRunner account. The server URL is the same for every tool: https://app.flowrunner.ai/mcp.

• Claude (web and desktop): open Settings > Connectors, click + Add, then Add custom connector. Enter FlowRunner and the server URL, click Add, then Connect, and approve the FlowRunner sign-in. On a Team or Enterprise plan, an Owner adds it once under Organization settings > Connectors.
• Claude Code: run these two commands in your project folder, and approve the sign-in page that opens:

claude mcp add --transport http flowrunner https://app.flowrunner.ai/mcp
claude mcp login flowrunner

• ChatGPT (on the web): open ChatGPT Plugins, click Add, then Add custom MCP server. Enter FlowRunner, put the server URL under Connection, choose OAuth, and approve the sign-in. In a chat, type @ and pick FlowRunner.
• Codex: add the server to ~/.codex/config.toml, then run codex mcp login flowrunner:

[mcp_servers.flowrunner]
url = "https://app.flowrunner.ai/mcp"

• Cursor: add the server to ~/.cursor/mcp.json, then open Customize > MCPs and follow the sign-in prompt:

{
  "mcpServers": {
    "flowrunner": { "url": "https://app.flowrunner.ai/mcp" }
  }
}

If you don't have a FlowRunner account yet, the Free plan needs no card, and every new account starts with 14 days of Professional. The setup guide in the docs has each tool step by step.

3. Convert one scenario at a time

Start a new chat, paste this request, then paste one blueprint after it:

Rebuild this Make scenario as a FlowRunner flow. It’s a blueprint from Make’s Export blueprint: the JSON lists the modules in order with their settings and mapped values, plus any routers, filters, and error handlers. It doesn’t include connections or the schedule. Keep the same behavior. Make runs each module once per bundle, so where a module received several bundles, use a loop over the list. Before you build, tell me anything you can’t map one to one, and ask me about anything the file doesn’t say.

Then add a line or two about what the blueprint can’t carry:

• how the scenario starts: its schedule, or the app or form that calls its webhook
• which data stores it uses and what they hold
• who approves, and on which channel, if a person signs off anywhere in the scenario

Answer its questions, and it builds the flow in your workspace. Make’s own tool modules (Set variable, Iterator, Aggregator, Sleep) become FlowRunner’s built-in blocks, and error handlers become error paths you can see on the canvas. One scenario per chat keeps the questions specific.

4. Finish what the blueprint can’t carry

Each conversion ends with a short list from the AI. Expect some of these:

• Connect your accounts. Each one is connected once and shared across your flows. The AI tells you which ones the flow needs.
• Fill in keys and secrets. API keys in an HTTP module’s headers, for example. The AI asks for each one or tells you where it goes.
• Set the schedule. Use the clock icon in the flow editor, or ask the AI to set it.
• Note the new address. Every app or form that posts to a Make custom webhook will need the flow’s External Callback URL when you switch over in step 5.
• Move data store records. Values a single flow keeps between runs fit in its Shared Memory. A table several flows share belongs in a spreadsheet or database the flows connect to.
• Set up approvals. If a person signs off by webhook, Slack, or email today, the AI builds that as a human-in-the-loop step. Tell it who reviews and on which channel: email, Slack, WhatsApp, phone, or a Form.
• Add forms and agent tools in the editor. FlowRunner Prompt to Flow can’t create a Form yet, or attach a flow to an AI agent as its tool. If the scenario needs either, the AI tells you which to add in the flow editor.
• Start the flow, if the AI left it stopped.

5. Test, then switch over

Run each flow with the inputs you saved in step 1 and compare the results with what the scenario produced. With FlowRunner Prompt to Flow connected you can ask your AI tool to do it, for example “Run my Order sync flow with this order.” A test run is a real run and counts as an execution.

When the results match, point the webhook callers at the flow’s new address, turn the scenario’s schedule off in Make, and watch the flow’s runs for a few days before you delete anything.

How Make maps to FlowRunner

Make	FlowRunner	What changes
Scenario	Flow	A flow can start with any block, not only a trigger.
Module	Block	One run is one execution, however many blocks run.
Schedule	Flow schedule	Once, every X seconds, daily, weekly, monthly, or cron.
Custom webhook	External Callback	New URL. The same block can also resume a paused run.
Filter	Condition	The No branch can do something instead of only stopping.
Router	Value Router or Condition	Where several routes ran for the same bundle, the AI asks how to lay them out.
Iterator	List Iterator	The steps for each item sit inside the loop.
Aggregator	A variable collected in the loop with Transform Data	Add To List builds the result one item at a time.
Set variable	Set Variables	Same idea, for the run.
Data store	Shared Memory	Belongs to one flow; shared tables go to a database or sheet.
Sleep	Wait	A run waits up to 30 days on Free, Starter, and Growth, and up to a year on Professional and up.
HTTP module	HTTP Request	A Retry Policy per request.
Error handlers and Incomplete Executions	Handle Error, plus Repeat and Wait	Failures get their own path on the canvas.
Connections	OAuth Connections	Connect each account once for the whole workspace.

Quick wins on day one

These are the differences you see as soon as the first scenario runs on FlowRunner. Each is covered in FlowRunner vs Make.

• One execution per run. A 3-module scenario over 10 items is roughly 31 Make credits. On FlowRunner the whole run is one execution.
• Longer waits. A Make run stops at 40 minutes on paid plans, and Sleep tops out at 5 minutes. A FlowRunner run waits up to 30 days on Free, Starter, and Growth, and up to a year on Professional and above.
• Approvals on every plan. Make’s Human in the Loop app is Enterprise-only and in closed beta. FlowRunner has human-in-the-loop on every plan, including Free, and the reviewer answers by email, Slack, WhatsApp, phone, or a Form.
• Compliance on published plans. Make signs no BAA on any plan and keeps audit and RBAC on Enterprise. FlowRunner has audit trails and RBAC from Professional ($299 a month) and signs a BAA on Business ($999 a month) and up.