DESTRUCTIVE. Defaults to dry-run; pass confirm=true to actually flip flags.
AI agents use email_mark to create or update resources in MCP Email Service — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Email Service environment.
Despite being labeled 'DESTRUCTIVE' by the server, marking/flagging emails is a reversible operation — flags can be toggled back. The dry-run default and confirm=true pattern suggests caution but the actual action (flipping flags) is a reversible write/update to email metadata, not a true destructive irreversible action. The sibling tool 'email_flag' likely overlaps.
From the tool's definition 'flip flags' and 'DESTRUCTIVE' label, but the action is marking/flagging emails (read/unread, flagged/unflagged) which is reversible state change
Documented attack patterns abuse exactly the kind of access email_mark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Email Service, and nothing reaches the server without passing your rules. This is the rule we recommend for email_mark:
{
"version": "1",
"default": "deny",
"tools": {
"email_mark": {
"limits": [
{
"counter": "email_mark_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}email_mark stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
DESTRUCTIVE. Defaults to dry-run; pass confirm=true to actually flip flags. It is categorised as a Write tool in the MCP Email Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Email Service MCP server in PolicyLayer and add a rule for email_mark: 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 MCP Email Service. Nothing to install.
email_mark 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 email_mark 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 email_mark. 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.
email_mark is provided by the MCP Email Service MCP server (leeguooooo/mailbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Email Service, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 MCP Email Service tools catalogued and risk-classified — across an index of 43,000+ MCP servers.