Conductor MCP Server

Instructions

Implementation Reference

• src/index.ts:1070-1082 (handler)

  The handler implementation for the 'get_task_logs' tool. It extracts the taskId from arguments, makes a GET request to the Conductor API endpoint `/tasks/${taskId}/log`, and returns the response data as a formatted JSON string in the MCP response format.

  case "get_task_logs": {
    const { taskId } = args as any;
    const response = await conductorClient.get(`/tasks/${taskId}/log`);
    
    return {
      content: [
        {
          type: "text",
          text: JSON.stringify(response.data, null, 2),
        },
      ],
    };
  }

• src/index.ts:471-480 (schema)

  Input schema definition for the 'get_task_logs' tool, specifying that a 'taskId' string is required.

  inputSchema: {
    type: "object",
    properties: {
      taskId: {
        type: "string",
        description: "The unique task execution ID",
      },
    },
    required: ["taskId"],
  },

• src/index.ts:467-481 (registration)

  Registration of the 'get_task_logs' tool in the tools array, including name, description, and input schema. This array is returned by the list_tools handler.

  {
    name: "get_task_logs",
    description:
      "Get execution logs for a specific task. Returns log entries generated during task execution.",
    inputSchema: {
      type: "object",
      properties: {
        taskId: {
          type: "string",
          description: "The unique task execution ID",
        },
      },
      required: ["taskId"],
    },
  },