How to move from Zapier to FlowRunner

This guide moves your Zaps to FlowRunner without rebuilding each one by hand. FlowRunner Prompt to Flow connects to the AI tool you already use, reads one Zap at a time, and builds the same workflow as a FlowRunner flow in your workspace.

On Zapier’s Team and Enterprise plans, the AI reads the JSON file Zapier exports. On Free and Professional, which can’t export, it reads screenshots of each step or the settings you copy out of the Zap editor. What’s left for you either way is connecting your accounts, filling in keys, and testing.

1. Export your Zaps from Zapier

Zapier’s help center lists Zap export as Team and Enterprise only (more on that limit). If you’re on Free or Professional, skip to “No export on your plan” below.

On Team or Enterprise:

1. Click your profile icon in the top right and select Settings.
2. In the left sidebar, under My account, click Security and data.
3. In Data management, click the download icon next to Download my Zap workflows, and save the file.

That gives you the Zaps you own. An account owner or super admin can use Download private and shared Zap workflows on the same page to export everyone’s Zaps. Zapier emails that file to the account email, and it also records whether each Zap was on or off.

The file is JSON (Zapier’s only export format). It describes each Zap’s trigger and steps with their settings. Plan on reconnecting every app, because working app connections don’t travel; Zapier’s own import asks you to reconnect them too. Zapier’s help article doesn’t mention Tables or Interfaces, so plan as if they stay behind. Run history has its own export.

No export on your plan: use one of these instead. Both work.

• Screenshots. Open the Zap in the editor and take a screenshot of each step, starting with the trigger, with its settings panel open so the app, the event, and the fields show. If a step has more fields than fit, take two.
• Copied settings. Write each step out as text: the app, the event, and every field with its value or mapping. A plain list is enough:

Trigger: Gmail, New Email Matching Search. Search string: label:invoices
Step 2: Filter. Only continue if Subject contains "Invoice"
Step 3: OpenAI, Extract structured data from Step 1 Body Plain
Step 4: Google Sheets, Create Spreadsheet Row. Sheet: Invoices. Amount: Step 3 total

Whichever route you take, save a few real runs from each Zap’s history while you’re there: what came in and what each step produced. You’ll test the new flow with them in step 5.

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 Zap at a time

Start a new chat for each Zap and paste the request that matches what you have.

For Zapier’s JSON export:

Rebuild this Zap as a FlowRunner flow. It comes from Zapier’s “Download my Zap workflows” export: the JSON describes the trigger and each step in order, with the app, the event, and the field settings and mapped values. Convert only the Zap named [Zap name]. The file doesn’t carry working app connections. Keep the same behavior: Filters and Paths become conditions or routers, and Code by Zapier steps become JavaScript. Before you build, tell me anything you can’t map one to one, and ask me about anything the file doesn’t say.

For screenshots:

Rebuild this Zap as a FlowRunner flow. My Zapier plan can’t export, so I’ve attached a screenshot of each step in order, starting with the trigger. Each one shows the app, the event, and the fields with their values or mappings. Here’s what the Zap does: [one or two sentences, for example “when an invoice email arrives, pull out the amount and add a row to our Invoices sheet”]. Keep the same behavior. Before you build, tell me anything you can’t map one to one, and ask me about anything the screenshots don’t show, like fields that didn’t fit on screen, Filter rules, or which Path runs when.

For copied settings:

Rebuild this Zap as a FlowRunner flow. My Zapier plan can’t export, so below is each step in order, starting with the trigger, copied from the Zap editor: the app, the event, and each field with its value or mapping. Keep the same behavior. Before you build, tell me anything you can’t map one to one, and ask me about anything my notes don’t say.

Answer its questions, and it builds the flow in your workspace. A Code by Zapier step comes across as JavaScript, and a Python one is rewritten in JavaScript for you to check. One Zap per chat keeps the questions specific.

4. Finish what the export can’t carry

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

• Connect your accounts. Each app is connected once and shared across your flows. The AI tells you which ones the flow needs.
• Fill in keys and secrets. API keys that sat in a Webhooks by Zapier step’s headers, for example. The AI asks for each one or tells you where it goes.
• Set the schedule. A Schedule by Zapier trigger becomes the flow’s schedule. Check the time and time zone.
• Note the new address. Every app or form that posts to a Zapier Catch Hook URL will need the flow’s External Callback URL when you switch over in step 5.
• Check the approvals. A Request Approval step becomes a human-in-the-loop step. Tell the AI 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 Zap needs either, the AI tells you which to add in the flow editor.
• Find a home for Tables data. If a Zap read or wrote a Zapier Table, move that data to a spreadsheet or database the flow connects to.
• Start the flow, if the AI left it stopped.

5. Test, then switch over

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

When the results match, point anything that called the Zap at the flow’s new address, turn the Zap off, and watch the flow’s runs for a few days before you delete anything in Zapier.

How Zapier maps to FlowRunner

Zapier	FlowRunner	What changes
Zap	Flow	A flow can start with any block, not only a trigger.
Trigger	The app’s trigger block	Same idea. Scheduled flows and API calls can start a flow too.
Action step	The app’s action block	One run is one execution, however many steps it has.
Filter	Condition	The No branch can do something instead of only stopping.
Paths	Condition or Value Router	A Value Router sends the run down a named branch for each value.
Formatter by Zapier	Transform Data	Text, number, date, and list operations as one block.
Looping by Zapier	List Iterator	Approvals can sit inside the loop.
Delay	Wait	A run waits up to 30 days on Free, Starter, and Growth, and up to a year on Professional and up.
Code by Zapier	Custom Cloud Code	JavaScript, with fetch. Python steps are rewritten in JavaScript.
Webhooks by Zapier (Catch Hook)	External Callback	New URL. The same block can also resume a paused run.
Webhooks by Zapier (outgoing)	HTTP Request	A Retry Policy per request.
Storage by Zapier	Shared Memory	Values a flow keeps from one run to the next.
Autoreplay	Handle Error, plus Repeat and Wait	Failures get their own path on the canvas.
Request Approval	A human-in-the-loop flow	The reviewer answers in email, Slack, WhatsApp, phone, or a Form, and an AI agent can call it as a tool.

Quick wins on day one

Each of these is covered in FlowRunner vs Zapier.

• One execution per run. A 10-step Zap run 1,000 times a month is roughly 10,000 Zapier tasks. On FlowRunner it’s 1,000 executions, however many steps you add later.
• Everyone gets a seat. Zapier has one user on Free and Professional and 25 on Team. FlowRunner has unlimited users on every plan, including Free.
• Approvals for the whole team. On Zapier Professional, a reviewer can only send approvals to themselves. FlowRunner has human-in-the-loop on every plan, and the reviewer answers by email, Slack, WhatsApp, phone, or a Form.
• Longer waits. Zapier’s Delay holds a Zap for up to 30 days. A FlowRunner run waits up to a year on Professional and above.
• Health data is allowed. Zapier signs no BAA on any plan. FlowRunner signs one on Business ($999 a month) and up, and audit trails and RBAC start at Professional ($299 a month).