AI agents use modify_email to create or update resources in Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail environment.
Modifying labels is a write operation that reorganizes data. It is reversible (labels can be changed back), so it does not meet the Destructive threshold. It does not execute code, move money, or trigger external operations beyond Gmail's label system.
From the tool's definition Tool description states it 'Modifies email labels (move to different folders)' — this is a reversible modification operation that changes email metadata/organization without deleting or executing arbitrary code.
Attacks that exploit this kind of access
Modifies email labels (move to different folders). It is categorised as a Write tool in the Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail MCP server in PolicyLayer and add a rule for modify_email: 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 Gmail. Nothing to install.
modify_email 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_email 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_email. 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_email is provided by the Gmail MCP server (pouyanafisi/gmail-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 →