AI agents use set_labels to create or update resources in Mail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mail environment.
Setting labels modifies email message state reversibly—labels can be added, removed, or changed without deleting data or executing code. This is a write operation with medium blast radius: an agent could mislabel large quantities of messages (potential disruption to email organization and filtering) but cannot permanently delete data, move money, or execute arbitrary code.
From the tool's definition Tool name 'set_labels' on an IMAP/SMTP email server indicates modification of message metadata (labels/tags). IMAP supports label operations which are reversible write operations on email messages.
Attacks that exploit this kind of access
set_labels. It is categorised as a Write tool in the Mail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mail MCP server in PolicyLayer and add a rule for set_labels: 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 Mail. Nothing to install.
set_labels 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 set_labels 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 set_labels. 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.
set_labels is provided by the Mail MCP server (kpihx/mail-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 →