Modify labels on a Gmail message.
AI agents use modify_gmail_message 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.
This tool modifies Gmail message labels (tags/folders), which is a reversible Write operation. It does not delete messages (Destructive), execute code (Execute), process payments (Financial), or merely read data (Read).
From the tool's definition Tool name is 'modify_gmail_message' and description states it 'Modify labels on a Gmail message.' Labels are metadata that can be added, removed, or changed, representing reversible modifications to message organization rather than permanent deletion or…
Attacks that exploit this kind of access
Modify labels on a Gmail message. 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 modify_gmail_message: 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.
modify_gmail_message 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 modify_gmail_message 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 modify_gmail_message. 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.
modify_gmail_message 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 →