Star a Google Task
AI agents use star_task 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.
Starring a task is a reversible metadata update operation that changes the task's flag status but does not create, delete, or destroy data. This is a write operation with minimal blast radius—worst case, tasks are unnecessarily starred or unstarred, causing minimal disruption. The operation is easily reversible by unstarring.
From the tool's definition Tool name 'star_task' and description 'Star a Google Task' indicates modification of task metadata (starring/flagging status) without deletion or creation of new data.
Attacks that exploit this kind of access
Star a Google Task. 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 star_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 Google Connections. Nothing to install.
star_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 star_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 star_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.
star_task 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 →