Skip to main content
Glama
DiversioTeam

ClickUp MCP Server

by DiversioTeam

create_task

Add new tasks to ClickUp lists with titles, descriptions, assignees, priorities, due dates, and time estimates for organized project management.

Instructions

Create a new task in a specific list

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTask title
descriptionNoTask description
list_nameNoName of the list to create task in
list_idNoID of the list (alternative to list_name)
assigneesNoUser IDs to assign
priorityNoPriority (1=urgent, 2=high, 3=normal, 4=low)
due_dateNoDue date (ISO 8601 format)
time_estimateNoTime estimate (e.g., '2h 30m')

Implementation Reference

  • Primary implementation of the 'create_task' tool handler. Resolves list by name if needed, builds CreateTaskRequest from parameters, calls client.create_task API wrapper, and returns formatted task information.
    async def create_task(
        self,
        title: str,
        description: Optional[str] = None,
        list_name: Optional[str] = None,
        list_id: Optional[str] = None,
        assignees: Optional[List[int]] = None,
        priority: Optional[int] = None,
        due_date: Optional[str] = None,
        time_estimate: Optional[str] = None,
        **kwargs: Any,
    ) -> Dict[str, Any]:
        """Create a new task."""
        # Find list ID if name provided
        if not list_id and not list_name:
            raise ValueError("Either list_id or list_name must be provided")
    
        if not list_id:
            lst = await self.client.find_list_by_name(list_name)
            if not lst:
                return {"error": f"List '{list_name}' not found"}
            list_id = lst.id
    
        # Build task request
        task_request = CreateTaskRequest(name=title)
    
        if description:
            task_request.description = description
        if assignees:
            task_request.assignees = assignees
        if priority:
            task_request.priority = priority
        if due_date:
            # Parse ISO date to unix timestamp
            dt = datetime.fromisoformat(due_date.replace("Z", "+00:00"))
            task_request.due_date = int(dt.timestamp() * 1000)
            task_request.due_date_time = True
        if time_estimate:
            task_request.time_estimate = parse_duration(time_estimate)
    
        # Create task
        task = await self.client.create_task(list_id, task_request)
    
        result = {
            "id": task.id,
            "name": task.name,
            "status": task.status.status,
            "url": format_task_url(task.id),
            "list": task.list.get("name", "Unknown"),
            "created": True,
        }
    
        if task.custom_id:
            result["custom_id"] = task.custom_id
    
        return result
  • Input schema definition for the 'create_task' tool, defining parameters like title (required), description, list_name or list_id, assignees, priority, due_date, and time_estimate.
    Tool(
        name="create_task",
        description="Create a new task in a specific list",
        inputSchema={
            "type": "object",
            "properties": {
                "title": {"type": "string", "description": "Task title"},
                "description": {"type": "string", "description": "Task description"},
                "list_name": {
                    "type": "string",
                    "description": "Name of the list to create task in",
                },
                "list_id": {
                    "type": "string",
                    "description": "ID of the list (alternative to list_name)",
                },
                "assignees": {
                    "type": "array",
                    "items": {"type": "integer"},
                    "description": "User IDs to assign",
                },
                "priority": {
                    "type": "integer",
                    "description": "Priority (1=urgent, 2=high, 3=normal, 4=low)",
                },
                "due_date": {"type": "string", "description": "Due date (ISO 8601 format)"},
                "time_estimate": {
                    "type": "string",
                    "description": "Time estimate (e.g., '2h 30m')",
                },
            },
            "required": ["title"],
        },
  • Registration of the 'create_task' handler method in the ClickUpTools class's internal tools dictionary, mapping the tool name to the handler function.
    self._tools: Dict[str, Callable] = {
        "create_task": self.create_task,
        "get_task": self.get_task,
        "update_task": self.update_task,
        "delete_task": self.delete_task,
        "list_tasks": self.list_tasks,
        "search_tasks": self.search_tasks,
        "get_subtasks": self.get_subtasks,
        "get_task_comments": self.get_task_comments,
        "create_task_comment": self.create_task_comment,
        "get_task_status": self.get_task_status,
        "update_task_status": self.update_task_status,
        "get_assignees": self.get_assignees,
        "assign_task": self.assign_task,
        "list_spaces": self.list_spaces,
        "list_folders": self.list_folders,
        "list_lists": self.list_lists,
        "find_list_by_name": self.find_list_by_name,
        # Bulk operations
        "bulk_update_tasks": self.bulk_update_tasks,
        "bulk_move_tasks": self.bulk_move_tasks,
        # Time tracking
        "get_time_tracked": self.get_time_tracked,
        "log_time": self.log_time,
        # Templates
        "create_task_from_template": self.create_task_from_template,
        "create_task_chain": self.create_task_chain,
        # Analytics
        "get_team_workload": self.get_team_workload,
        "get_task_analytics": self.get_task_analytics,
        # User management
        "list_users": self.list_users,
        "get_current_user": self.get_current_user,
        "find_user_by_name": self.find_user_by_name,
    }
  • Low-level ClickUpClient method that performs the actual HTTP POST request to the ClickUp API to create a task, using the CreateTaskRequest model.
    async def create_task(
        self,
        list_id: str,
        task: CreateTaskRequest,
    ) -> Task:
        """Create a new task."""
        data = await self._request(
            "POST",
            f"/list/{list_id}/task",
            json=task.model_dump(exclude_none=True),
        )
        return Task(**data)
  • Pydantic model defining the structure for task creation data, used by the client to serialize parameters for the ClickUp API.
    class CreateTaskRequest(BaseModel):
        """Request model for creating a task."""
    
        name: str
        description: Optional[str] = None
        assignees: Optional[ListType[int]] = None
        tags: Optional[ListType[str]] = None
        status: Optional[str] = None
        priority: Optional[int] = None
        due_date: Optional[int] = None  # Unix timestamp in milliseconds
        due_date_time: Optional[bool] = False
        time_estimate: Optional[int] = None  # Time in milliseconds
        start_date: Optional[int] = None  # Unix timestamp in milliseconds
        start_date_time: Optional[bool] = False
        notify_all: Optional[bool] = True
        parent: Optional[str] = None
        links_to: Optional[str] = None
        custom_fields: Optional[ListType[Dict[str, Any]]] = None
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states 'Create a new task' which implies a write/mutation operation, but doesn't disclose behavioral traits like required permissions, whether the task is immediately active, error handling (e.g., if list doesn't exist), or response format. For a mutation tool with zero annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste—it directly states the tool's purpose without redundancy. It's appropriately sized and front-loaded, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given this is a mutation tool (creating tasks) with no annotations and no output schema, the description is incomplete. It doesn't cover success/error responses, side effects (e.g., notifications to assignees), or constraints (e.g., max tasks per list). For a tool with 8 parameters and complex sibling relationships, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 8 parameters with clear descriptions (e.g., priority levels explained). The description adds no additional meaning beyond implying 'list_name' or 'list_id' is needed for the 'specific list' context, but this is already covered in schema. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create a new task') and target resource ('in a specific list'), which is a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'create_task_from_template' or 'create_task_chain', which also create tasks but with different approaches or contexts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'create_task_from_template' (for templated tasks) or 'bulk_create_tasks' (not listed but implied by bulk operations). It mentions 'in a specific list' but doesn't clarify prerequisites (e.g., list must exist) or exclusions (e.g., not for recurring tasks).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other 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/DiversioTeam/clickup-mcp'

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