Create a new Google Tasks task list
AI agents use create_task_list to create or update resources in Google Connections — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Connections environment.
Creating a new task list is a Write operation—it creates data that can be modified or deleted later, making it reversible. The severity is medium because while the blast radius is limited (a new task list is a relatively minor resource), an agent could be tricked into creating numerous task lists that clutter a user's workspace or consume organizational resources.
From the tool's definition Tool is named 'create_task_list' and explicitly described as 'Create a new Google Tasks task list'. This is a create operation that generates new data structure (a task list) in Google Tasks.
Attacks that exploit this kind of access
Create a new Google Tasks task list. It is categorised as a Write tool in the Google Connections MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Connections MCP server in PolicyLayer and add a rule for create_task_list: 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 Google Connections. Nothing to install.
create_task_list 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_list 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_list. 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_list is provided by the Google Connections MCP server (michaelzrork/google-connections-mcp). 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 →