Star one or more Gmail messages
AI agents use star_gmail 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 emails modifies message metadata/state but does not create, delete, or permanently alter message content. The operation is fully reversible (messages can be unstarred). While it affects user data organization, the impact is limited to adding a label/flag without exposing sensitive content or executing external operations.
From the tool's definition Tool name 'star_gmail' and description 'Star one or more Gmail messages' indicate a modification operation that adds a star label/flag to Gmail messages. This is a reversible state change to email metadata.
Attacks that exploit this kind of access
Star one or more Gmail messages. 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_gmail: 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_gmail 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_gmail 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_gmail. 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_gmail 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 →