Creates a new task that must be executed. If decomposing a complex task is required, must use 'decompose_task' first before executing it. All tasks start in the todo status. Must use 'update_task' before executing this task, and when executing this task has finished.
AI agents use create_task to create or update resources in Mcp Task Manager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Task Manager environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
goal | string | Yes | The overall goal of this task. Must be understandable out of context |
title | string | Yes | A concise title for this task. Must be understandable out of context |
description | string | Yes | A detailed description of this task. Must be understandable out of context |
criticalPath | boolean | Yes | Whether this task is on the critical path and required for completion |
uncertaintyAreas | array | Yes | A detailed list of areas where there is uncertainty about this task's requirements or execution. Must be understandable out of context. May be empty. |
definitionsOfDone | array | Yes | A detailed list of criteria that must be met for this task to be considered 'complete'. Must be understandable out of context. |
estimatedComplexity | object | Yes | An estimate of the complexity of this task. All tasks with complexity higher than low must be decomposed into smaller, more manageable subtasks before execution |
Parameters from the server's own tool schema.
This is a Write operation because it creates and persists new task records in a reversible manner. The severity is medium rather than high because while task creation could be abused to flood the system or create misleading work items, the impact is limited to task metadata rather than critical system resources, financial transactions, or permanent data destruction.
From the tool's definition Tool description states 'Creates a new task that must be executed.' The verb 'Creates' and the instruction 'All tasks start in the todo status' indicate this tool adds new data to the task management system.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
Creates a new task that must be executed. If decomposing a complex task is required, must use 'decompose_task' first before executing it. All tasks start in the todo status. Must use 'update_task' before executing this task, and when executing this task has finished. It is categorised as a Write tool in the Mcp Task Manager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_task accepts 7 parameters: goal, title, description, criticalPath, uncertaintyAreas, definitionsOfDone, estimatedComplexity. Required: goal, title, description, criticalPath, uncertaintyAreas, definitionsOfDone, estimatedComplexity. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Task Manager MCP server in PolicyLayer and add a rule for create_task: 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 Mcp Task Manager. Nothing to install.
create_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_task 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.
Set action: deny in the PolicyLayer policy for create_task. 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.
create_task is provided by the Mcp Task Manager MCP server (@blizzy/mcp-task-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →