Skip to main content
Glama

mark_task_done

Mark a specific task as completed by providing 'requestId' and 'taskId'. Optionally add 'completedDetails' for context. Displays updated task progress and requires user approval before proceeding.

Instructions

Mark a given task as done after you've completed it. Provide 'requestId' and 'taskId', and optionally 'completedDetails'.

After marking a task as done, a progress table will be displayed showing the updated status of all tasks.

After this, DO NOT proceed to 'get_next_task' again until the user has explicitly approved this completed task using 'approve_task_completion'.

Input Schema

NameRequiredDescriptionDefault
completedDetailsNo
requestIdYes
taskIdYes

Input Schema (JSON Schema)

{ "properties": { "completedDetails": { "type": "string" }, "requestId": { "type": "string" }, "taskId": { "type": "string" } }, "required": [ "requestId", "taskId" ], "type": "object" }

Implementation Reference

  • MCP tool handler that parses input arguments and delegates to the TaskFlowService's markTaskDone method.
    async mark_task_done(args: any) { const { requestId, taskId, completedDetails } = args ?? {}; return service.markTaskDone(String(requestId), String(taskId), completedDetails); },
  • Core implementation of task completion: validates preconditions (subtasks done), marks task as done, persists to file, generates progress table response.
    public async markTaskDone(requestId: string, taskId: string, completedDetails?: string) { await this.loadTasks(); const req = this.getRequest(requestId); if (!req) return { status: "error", message: "Request not found" }; const task = req.tasks.find((t) => t.id === taskId); if (!task) return { status: "error", message: "Task not found" }; if (task.done) return { status: "already_done", message: "Task is already marked done." }; const hasSubtasks = task.subtasks.length > 0; const allSubtasksDone = task.subtasks.every((s) => s.done); if (hasSubtasks && !allSubtasksDone) { return { status: "subtasks_pending", message: "Cannot mark task as done until all subtasks are completed.", pendingSubtasks: task.subtasks.filter((s) => !s.done).map((s) => ({ id: s.id, title: s.title })), }; } task.done = true; task.completedDetails = completedDetails || ""; await this.saveTasks(); const progressTable = formatTaskProgressTableForRequest(req); return { status: "task_marked_done", requestId: req.requestId, task: { id: task.id, title: task.title, description: task.description, completedDetails: task.completedDetails, subtasks: task.subtasks.map((s) => ({ id: s.id, title: s.title, description: s.description, done: s.done, })), }, message: `Task ${taskId} has been marked as done.\n${progressTable}`, }; }
  • JSON Schema defining the input parameters for the mark_task_done tool (requestId, taskId required; completedDetails optional).
    mark_task_done: { type: "object", properties: { requestId: { type: "string" }, taskId: { type: "string" }, completedDetails: { type: "string" }, }, required: ["requestId", "taskId"], },
  • Tool object definition with name, description, and inputSchema, exported and included in server registration for listTools.
    export const MARK_TASK_DONE_TOOL: Tool = { name: "mark_task_done", description: "Mark a given task as done after you've completed it. Provide 'requestId' and 'taskId', and optionally 'completedDetails'.\n\n" + "After marking a task as done, a progress table will be displayed showing the updated status of all tasks.\n\n" + "After this, DO NOT proceed to 'get_next_task' again until the user has explicitly approved the completed task. Ask the user for approval before continuing.", inputSchema: { type: "object", properties: { requestId: { type: "string" }, taskId: { type: "string" }, completedDetails: { type: "string" }, }, required: ["requestId", "taskId"], }, };
  • Server's listTools handler registers MARK_TASK_DONE_TOOL in the tools array provided to MCP clients.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: [ PLAN_TASK_TOOL, GET_NEXT_TASK_TOOL, MARK_TASK_DONE_TOOL, OPEN_TASK_DETAILS_TOOL, LIST_REQUESTS_TOOL, ADD_TASKS_TO_REQUEST_TOOL, UPDATE_TASK_TOOL, DELETE_TASK_TOOL, ADD_SUBTASKS_TOOL, MARK_SUBTASK_DONE_TOOL, UPDATE_SUBTASK_TOOL, DELETE_SUBTASK_TOOL, EXPORT_TASK_STATUS_TOOL, ADD_NOTE_TOOL, UPDATE_NOTE_TOOL, DELETE_NOTE_TOOL, ADD_DEPENDENCY_TOOL, GET_PROMPTS_TOOL, SET_PROMPTS_TOOL, UPDATE_PROMPTS_TOOL, REMOVE_PROMPTS_TOOL, ARCHIVE_COMPLETED_REQUESTS_TOOL, LIST_ARCHIVED_REQUESTS_TOOL, RESTORE_ARCHIVED_REQUEST_TOOL, ], }));

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/pinkpixel-dev/taskflow-mcp'

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