create_todo

SERVERUnClick SOURCE@unclick/mcp-server

Medium RISK CLASS

Category Write

Parameters 62 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/create-todo.md

WHAT IT DOES

What create_todo does on UnClick

AI agents use create_todo to create or update resources in UnClick, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.

Parameter	Type	Required	Description
`title`	string	Yes	Short title (max 200 chars)
`due_at`	string	—	Optional due date in ISO format. A date-only value like 2026-06-15 means due by the end of that day.
`agent_id`	string	Yes	Stable identifier for the calling agent. Same value as set_my_emoji.
`priority`	string	—
`description`	string	—	Optional longer description (max 4000 chars)
`assigned_to_agent_id`	string	—	Optional agent_id of the agent who should own this todo

Parameters from the server's own tool schema.

RISK

Why create_todo is rated Medium

This tool creates and posts data (a todo card and associated event) to a shared board system. The effects are reversible—todos can be edited, deleted, or marked complete without permanent data loss. There is no financial impact, no code execution, no destructive deletion, and no irreversible side effects.

From the tool's definition Creates a new todo card on the shared Jobs board; Posts a 'todo-created' Boardroom event. The tool modifies data by adding a new record to a kanban board, which is a reversible write operation.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_todo safely

PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_todo, this is the rule to start with:

create_todo Rate-limited

create_todo stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_todo": {
      "limits": [
        {
          "counter": "create_todo_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every create_todo call is checked against it from then on.

FAQ

Questions about create_todo

What does the create_todo tool do? +

Creates a new todo card on the shared Jobs board (the Boardroom Todos kanban; humans watch the same queue at /admin/jobs) so the agent pack and the human both see what's on deck. Use when you decide an action item needs tracking beyond a single message: a follow-up task, a chore, a deliverable. Provide agent_id (yours), a short title, and optional description, priority, and assignee. Posts a 'todo-created' Boardroom event so other agents notice without polling. When a forge PR finishes the job, put 'Closes UnClick todo: <uuid>' in the PR body and the merge auto-completes the card. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_todo accept? +

create_todo accepts 6 parameters: title, due_at, agent_id, priority, description, assigned_to_agent_id. Required: title, agent_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_todo? +

Register the UnClick MCP server in PolicyLayer and add a rule for create_todo: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.

What risk level is create_todo? +

create_todo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_todo? +

Yes. Add a rate_limit block to the create_todo rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_todo completely? +

Set action: deny in the PolicyLayer policy for create_todo. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_todo? +

create_todo is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on UnClick, and thousands of servers like it.

This server

All 1662 UnClick tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →