start_workflow
Execute automated workflows in Agentled MCP Server by providing workflow ID and optional input data for process initiation.
Instructions
Start a workflow execution. Optionally provide input data that maps to the workflow's input page fields. For example, if the workflow expects "company_url", pass: { input: { company_url: "https://..." } }
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| workflowId | Yes | The workflow ID to start | |
| input | No | Input payload matching the workflow input page fields | |
| metadata | No | Optional execution metadata |
Implementation Reference
- src/tools/executions.ts:11-30 (registration)The `start_workflow` tool is registered here, which invokes the `client.startWorkflow` method.
server.tool( 'start_workflow', `Start a workflow execution. Optionally provide input data that maps to the workflow's input page fields. For example, if the workflow expects "company_url", pass: { input: { company_url: "https://..." } }`, { workflowId: z.string().describe('The workflow ID to start'), input: z.record(z.string(), z.any()).optional().describe('Input payload matching the workflow input page fields'), metadata: z.record(z.string(), z.any()).optional().describe('Optional execution metadata'), }, async ({ workflowId, input, metadata }, extra) => { const client = clientFactory(extra); const result = await client.startWorkflow(workflowId, input, metadata); return { content: [{ type: 'text' as const, text: JSON.stringify(result, null, 2), }], }; } );