Cascades Docs
Sign in to run requests with your own sandbox key. Sign in
View as Markdown Open in Claude Open in ChatGPT Add MCP server

MCP tool

cascades_generate_workflow

write workflows:write

Build a cascade from a plain-English policy description using the Cascades AI builder, then create it (by default) so it is immediately runnable with cascades_trigger_workflow. Use this when the user describes a screening/decision policy in words rather than supplying a node graph. Returns the created cascade (with the AI-generated name and any warnings); pass create:false to preview the generated definition without saving it.

REST operation

This tool makes one call: POST /api/v1/workflows/generate — see generateWorkflow in the API reference for the full response schema and error codes.

Input schema

ArgumentTypeDescription
prompt required string Plain-English description of the decision policy to turn into a cascade (max 5 000 characters by default).
name string Optional name override; otherwise the generator names the cascade.
use_case string Optional use case label. Defaults to `tenant_screening`.
create boolean `true` (default) saves the generated cascade and returns `201`; `false` returns the generated definition as a `200` preview without saving.
environment string Target environment: "prod" (default) or "dev".
One of: dev prod

Example

What the model sends, and the JSON the tool returns (the REST response, verbatim).

Call
{
  "name": "cascades_generate_workflow",
  "arguments": {
    "prompt": "Approve applicants with a credit score over 680 and no evictions; refer everyone else to review.",
    "use_case": "tenant_screening"
  }
}
Result
{
  "data": {
    "id": 159,
    "object": "workflow",
    "name": "Score 680+ and no evictions",
    "active": true
  },
  "warnings": []
}

Other tools