Skip to main content
Glama

retry_workflow

Restart failed workflow executions from the last failed task in Netflix Conductor. Use this tool to troubleshoot and resume interrupted workflows by specifying the workflow ID.

Instructions

Retry a failed workflow execution from the last failed task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowIdYesThe workflow execution ID to retry
resumeSubworkflowTasksNoResume subworkflow tasks (default: false)

Implementation Reference

  • Executes the retry_workflow tool by sending a POST request to Conductor's /workflow/{workflowId}/retry endpoint with optional resumeSubworkflowTasks parameter. Returns success message.
    case "retry_workflow": {
      const { workflowId, resumeSubworkflowTasks = false } = args as any;
      await conductorClient.post(`/workflow/${workflowId}/retry`, null, {
        params: { resumeSubworkflowTasks },
      });
      
      return {
        content: [
          {
            type: "text",
            text: `Workflow ${workflowId} retry initiated successfully.`,
          },
        ],
      };
    }
  • Defines the tool schema including name, description, and input schema requiring workflowId (string) and optional resumeSubworkflowTasks (boolean). This also serves as registration in the tools array.
      name: "retry_workflow",
      description:
        "Retry a failed workflow execution from the last failed task.",
      inputSchema: {
        type: "object",
        properties: {
          workflowId: {
            type: "string",
            description: "The workflow execution ID to retry",
          },
          resumeSubworkflowTasks: {
            type: "boolean",
            description: "Resume subworkflow tasks (default: false)",
          },
        },
        required: ["workflowId"],
      },
    },
  • src/index.ts:598-602 (registration)
    Registers all tools including retry_workflow by returning the tools array in response to ListToolsRequestSchema.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools,
      };
    });

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/opensensor/conductor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server