Skip to main content
Glama
elizagarate

Things MCP Server

by elizagarate

add_todo

Add a new task to Things 3 with title, notes, schedule, deadline, tags, checklist items, and assign to projects or headings.

Instructions

Create a new todo in Things

Args: title: Title of the todo notes: Notes for the todo when: When to schedule the todo (today, tomorrow, evening, anytime, someday, or YYYY-MM-DD). Use YYYY-MM-DD@HH:MM format to add a reminder (e.g., 2024-01-15@14:30) deadline: Deadline for the todo (YYYY-MM-DD) tags: Tags to apply to the todo checklist_items: Checklist items to add list_id: ID of project/area to add to list_title: Title of project/area to add to heading: Heading title to add under heading_id: Heading ID to add under (takes precedence over heading)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYes
notesNo
whenNo
deadlineNo
tagsNo
checklist_itemsNo
list_idNo
list_titleNo
headingNo
heading_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • MCP tool handler for add_todo. Registered with @mcp.tool decorator. Builds a Things URL via url_scheme.add_todo() and executes it via url_scheme.execute_url().
    @mcp.tool
    async def add_todo(
        title: str,
        notes: str = None,
        when: str = None,
        deadline: str = None,
        tags: List[str] = None,
        checklist_items: List[str] = None,
        list_id: str = None,
        list_title: str = None,
        heading: str = None,
        heading_id: str = None
    ) -> str:
        """Create a new todo in Things
    
        Args:
            title: Title of the todo
            notes: Notes for the todo
            when: When to schedule the todo (today, tomorrow, evening, anytime, someday, or YYYY-MM-DD).
                Use YYYY-MM-DD@HH:MM format to add a reminder (e.g., 2024-01-15@14:30)
            deadline: Deadline for the todo (YYYY-MM-DD)
            tags: Tags to apply to the todo
            checklist_items: Checklist items to add
            list_id: ID of project/area to add to
            list_title: Title of project/area to add to
            heading: Heading title to add under
            heading_id: Heading ID to add under (takes precedence over heading)
        """
        url = url_scheme.add_todo(
            title=title,
            notes=notes,
            when=when,
            deadline=deadline,
            tags=tags,
            checklist_items=checklist_items,
            list_id=list_id,
            list_title=list_title,
            heading=heading,
            heading_id=heading_id
        )
        url_scheme.execute_url(url)
        return f"Created new todo: {title}"
  • URL construction function for add_todo. Defines all parameters and builds a 'things:///add' URL with proper encoding of tags, checklist items, and other params.
    def add_todo(title: str, notes: Optional[str] = None, when: Optional[str] = None,
                 deadline: Optional[str] = None, tags: Optional[list[str]] = None,
                 checklist_items: Optional[list[str]] = None, list_id: Optional[str] = None,
                 list_title: Optional[str] = None, heading: Optional[str] = None,
                 heading_id: Optional[str] = None,
                 completed: Optional[bool] = None) -> str:
        """Construct URL to add a new todo.
    
        Args:
            title: Title of the todo
            notes: Notes for the todo
            when: Schedule the todo. Accepts:
                - Keywords: "today", "tomorrow", "evening", "anytime", "someday"
                - Date: "yyyy-mm-dd" or natural language ("in 3 days", "next tuesday")
                - DateTime (adds reminder): "yyyy-mm-dd@HH:MM" (e.g., "2024-01-15@14:30")
            deadline: Deadline date (yyyy-mm-dd)
            tags: List of tag names
            checklist_items: List of checklist item titles
            list_id: UUID of project/area to add to
            list_title: Title of project/area to add to
            heading: Heading title within project
            heading_id: UUID of heading within project
            completed: Mark as completed on creation
        """
        params = {
            'title': title,
            'notes': notes,
            'when': when,
            'deadline': deadline,
            'checklist-items': '\n'.join(checklist_items) if checklist_items else None,
            'list-id': list_id,
            'list': list_title,
            'heading': heading,
            'heading-id': heading_id,
            'completed': completed
        }
    
        # Handle tags separately since they need to be comma-separated
        if tags:
            params['tags'] = ','.join(tags)
        return construct_url('add', {k: v for k, v in params.items() if v is not None})
  • Executes the constructed Things URL via macOS 'open -g' command with security validation to prevent opening arbitrary URLs.
    def execute_url(url: str) -> None:
        """Execute a Things URL without bringing Things to the foreground.
        
        Security: validates the URL starts with 'things:///' before execution
        to prevent opening arbitrary URLs or executing unintended commands.
        Uses subprocess with argument list (no shell interpolation) to avoid
        command injection vectors.
        """
        if not url.startswith("things:///"):
            raise ValueError(f"Invalid Things URL scheme: {url[:50]}")
        subprocess.run(['open', '-g', url], check=True, capture_output=True)
  • URL construction helper. Builds 'things:///{command}' with URL-encoded query parameters, handling booleans and lists.
    def construct_url(command: str, params: Dict[str, Any]) -> str:
        """Construct a Things URL from command and parameters."""
        # Start with base URL
        url = f"things:///{command}"
    
        # Get authentication token if needed
        if command in ['update', 'update-project']:
            token = things.token()
            if token:
                params['auth-token'] = token
    
        # URL encode parameters
        if params:
            encoded_params = []
            for key, value in params.items():
                if value is None:
                    continue
                # Handle boolean values
                if isinstance(value, bool):
                    value = str(value).lower()
                # Handle lists (for tags, checklist items etc)
                elif isinstance(value, list):
                    value = ','.join(str(v) for v in value)
                encoded_params.append(f"{key}={urllib.parse.quote(str(value))}")
    
            url += "?" + "&".join(encoded_params)
    
        return url
  • Tool registration via @mcp.tool decorator on FastMCP instance. The decorator registers the function as an MCP tool named 'add_todo'.
    # Things URL Scheme tools
    @mcp.tool
    async def add_todo(
Behavior2/5

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

No annotations provided, so the description must carry the full burden. It only says 'Create', indicating mutation, but fails to disclose side effects, authentication needs, rate limits, or what happens on duplication. Minimal behavioral context.

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

Conciseness4/5

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

The description is front-loaded with the purpose and then lists parameters concisely. Each parameter line is necessary, but the format could be slightly more compact. Still efficient and well-structured.

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

Completeness3/5

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

Output schema exists, so return values are covered. However, the description lacks information about errors, constraints, or behavior when parameters conflict. For a creation tool with 10 parameters and no annotations, this is a moderate shortfall.

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

Parameters4/5

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

All 10 parameters are explained in the description, including format details for 'when' and 'deadline', and relationships like 'heading_id takes precedence over heading'. This adds significant value beyond the schema, which has 0% description coverage.

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

Purpose5/5

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 todo') and the resource ('in Things'), using a specific verb and resource. It distinguishes from sibling tools like update_todo and add_project.

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?

No explicit guidance on when to use this tool vs. alternatives. Only the purpose is stated, leaving the agent to infer that creation is appropriate, but without any context about prerequisites or when not to use it.

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/elizagarate/things-mcp'

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