How to move from Workato to FlowRunner

This guide moves your Workato recipes to FlowRunner without rebuilding each one by hand. You export a package of recipe files from Workato, and FlowRunner Prompt to Flow reads one recipe at a time and builds the same workflow as a FlowRunner flow, in your workspace.

What’s left for you is the part no export carries: connecting your accounts, adding keys, and testing each flow against what the recipe did. For how the two platforms compare, see FlowRunner vs Workato.

1. Export your recipes from Workato

Workato exports recipes through recipe lifecycle management (RLCM).

1. Open Tools > Recipe lifecycle management and go to the Export tab.
2. Create a manifest. Give it a name and pick the source folder. Workato adds the recipes in that folder and its subfolders, plus the assets they depend on. You can also include tags.
3. For each lookup table, choose Include data or Ignore data. The default is Ignore data, so pick Include data if you want the rows.
4. Save the manifest, click Build and export package, and download the .zip. Past builds stay in the manifest’s Export history.

The package is a zip of JSON files, one per asset: recipes, connections, recipe functions, lookup tables, custom SDK connectors, and more. Download it soon after you build it, because Workato keeps packages only for your workspace’s data period.

What the package leaves out:

• Credentials. Workato says that “exporting a package does not export any credentials, keys, or other private data.” A connection carries only its name, app type, and other non-sensitive details.
• Lookup table rows, unless you chose Include data.
• Assets in other projects. If a recipe calls something in another project, export that project too.

Workato’s docs don’t say which plans include RLCM. Workato now recommends Environments for moving recipes, which is on specific pricing plans, and says RLCM continues to work. If you can’t export a package, describe the recipe in the chat in step 3 and attach a screenshot of each step instead.

Before you switch anything off, write down a few recent jobs for each recipe, with their inputs, so you have real data to test with 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 recipe at a time

Unzip the package. Start a new chat, paste this request, then attach or paste one recipe’s JSON file after it:

Rebuild this Workato recipe as a FlowRunner flow. It comes from a Workato recipe lifecycle management package, which is a zip of JSON files, one per asset. The recipe’s JSON lists the trigger and each step in order, with its connector, action, and field mappings, plus any IF conditions, Repeat loops, Monitor and Error blocks, and Call Recipe Function steps. Connections in the package are placeholders with only a name and app type, and Workato doesn’t export credentials. Keep the same behavior. Before you build, tell me anything you can’t map one to one, and ask me about anything the file doesn’t say.

If the recipe calls other recipes or reads a lookup table, add their files and this line:

This recipe calls the recipe functions in the other files and reads the lookup table I’ve attached. Build each called recipe as its own flow first, then the main one, and ask me where the lookup table’s data should live.

Then add a line or two about anything the file can’t tell it:

• who answers each approval (a Workflow apps request or a “Wait for user action” step), and whether by email, Slack, WhatsApp, or phone
• which steps use Python snippets, so it can rewrite them in JavaScript or call your code as a service
• which AI provider and model a Genie or AI step used

Answer its questions, and it builds the flow. One recipe per chat keeps the questions specific.

4. Finish what the export can’t carry

Each conversion ends with a short list of what’s left. Expect some of these:

• Connect your accounts. Each app is connected once in the workspace and shared across your flows.
• Add keys and secrets. FlowRunner runs AI agents on your own provider key, added once. API keys for an HTTP Request block go in its headers.
• Set the schedule. Check each scheduled flow’s timing against the recipe’s trigger before you start it.
• Note the new address. A recipe that started from a webhook gets a new External Callback URL. That URL includes your workspace key, so treat it like a password, and give it to the calling app when you switch over.
• Check the approvals. The AI sets up each approval request in the channel you named. Two things are added in the flow editor: a Form, if people should answer through one, and an AI agent that calls another flow as its tool. The AI tells you which of these to add.
• Move lookup data. If you ignored lookup table data on export, copy the rows to wherever the AI suggested.
• Start the flow, if the AI left it stopped.

5. Test, then switch over

Run each flow with the job inputs you saved in step 1, and compare the results with what the recipe produced. Open the run in the flow’s Instances tab to see what each block received and returned. When the results match, point the calling apps and webhooks at FlowRunner, watch the runs for a few days, and stop the Workato recipe.

How Workato maps to FlowRunner

Workato	FlowRunner	What changes
Recipe	Flow	One run of a flow is one execution, however many steps it has.
Trigger (app event, scheduler, webhook)	Integration trigger, Flow Schedule, or External Callback	A flow can also start from any block when it’s called by API or another flow.
Action step	Integration action	2,100+ integrations, all on every plan.
IF condition, ELSE IF, ELSE	Condition or Value Router	The branches show on the canvas.
Repeat for each, Repeat while	List Iterator or Repeat	The same loop, as a block on the canvas.
Monitor and Error blocks	Handle Error	One Handle Error block can guard several blocks.
Call Recipe Function	Call Flow or a SubFlow	Call Flow can wait for the answer or let the called flow run on its own.
Lookup table	Shared Memory, or a sheet or database you connect	Shared Memory keeps key and value data across runs.
Connection	App connection	Connected once, shared across flows.
Workflow apps request, Wait for user action	Human-in-the-loop flow with an External Callback or a Form	On every plan; the person answers by email, Slack, WhatsApp, phone, or a Form.
Genie or AI step	AI Agent	Runs on your own provider key. An agent can call flows as tools.
Python snippets	Custom Cloud Code (JavaScript), or your Python service called with an HTTP Request	FlowRunner doesn’t run Python.
Job history	The flow’s Instances tab (inspecting a run)	Each run shows what every block received and returned.

Quick wins on day one

• Prices you can read. Free is $0 for 100 executions a month and Starter starts at $5, with no quote to wait for.
• One run, one execution. Adding a step to a flow doesn’t change what a run costs.
• Agents and approvals on every plan. Every integration, AI agents on your own keys, and human-in-the-loop come with every plan, including Free.
• Approvals in the person’s own channel. A request reaches them by email, Slack, WhatsApp, phone, or a Form, and a run waits up to 30 days on Free, Starter, and Growth, and up to a year on Professional and above.
• Audit at a listed price. Audit trails and RBAC come with Professional at $299 a month, and the 14-day trial on signup is Professional.