manage_workflows

Management

Manage Workflows

CRUD and execution for visual workflows. Actions: list, get, create, update, delete, run, approve, reject. Args: - action: required operation (see above) - workflow_id: required for get, update, delete, run, approve, reject - name, description, definition: used for create or update - inputs, dry_run: used for run - workflow_job_id, node_id: required for approve and reject - team_id, project_id: required for OAuth callers Returns: workflow metadata for CRUD calls, workflow run results for run, and approval results for approve/reject. Examples: - "List workflows" -> action="list" - "Run this workflow" -> action="run", workflow_id="workflow_xxx", inputs={...} - "Approve this workflow node" -> action="approve", workflow_id="workflow_xxx", workflow_job_id="job_xxx", node_id="node_xxx" Don't use when: You only need a single model invocation. Prefer run_model instead.

destructiveopen-world

Parameters

NameTypeRequiredDescription
actionenum(list | get | create | update | delete | run | approve | reject)Workflow action: list, get, create, update, delete, run, approve, or reject.
workflow_idstringWorkflow ID (required for most actions).
namestringWorkflow name (for create/update).
descriptionstringWorkflow description (for create/update).
definitionrecordWorkflow definition (for create/update).
inputsrecordInput values for run.
dry_runbooleanEstimate cost without running.
workflow_job_idstringJob ID (for approve/reject).
node_idstringNode ID (for approve/reject).
team_idstringTeam ID. Required if user belongs to multiple teams.
project_idstringProject ID to scope the operation to.
response_formatenum(json | markdown)jsonOutput format: 'json' for structured data, 'markdown' for human-readable text.

Example Request

JSON
{
  "action": "run",
  "workflow_id": "wf_hero_pipeline",
  "inputs": {
    "prompt": "epic fantasy hero portrait",
    "style_model_id": "model_custom_abc"
  },
  "team_id": "team_abc123",
  "project_id": "proj_xyz789"
}

Example Response

JSON
{
  "workflow": {
    "id": "wf_hero_pipeline",
    "status": "running",
    "jobId": "job_wf_001"
  }
}

Common Use Cases

  • Execute a multi-step generation pipeline in a single call
  • Dry-run a workflow to estimate credit cost before executing
  • Approve or reject a human-in-the-loop node in a paused workflow
  • Create and manage reusable workflow definitions for repeatable pipelines