既存タスクにサブタスクを追加します。
AI agents use add_subtask to create or update resources in TaskMateAI — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TaskMateAI environment.
This tool creates new subtask entities, which is a reversible modification operation. It does not execute arbitrary code, delete data, or affect financial systems. The action is Write-level because subtasks can be created, modified, or removed without permanent consequences.
From the tool's definition Tool description translates to 'Add a subtask to an existing task' - the verb indicates creation/modification of data (a subtask entity). Sibling tools like create_task, update_progress, and update_subtask confirm this is a Write-category server.
Attacks that exploit this kind of access
既存タスクにサブタスクを追加します。. It is categorised as a Write tool in the TaskMateAI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TaskMateAI MCP server in PolicyLayer and add a rule for add_subtask: 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 TaskMateAI. Nothing to install.
add_subtask 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 add_subtask 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 add_subtask. 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.
add_subtask is provided by the TaskMateAI MCP server (newaitees/taskmateai). 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 →