Set or unset flags on an email (e.g. \\\\Seen, \\\\Flagged).
AI agents use mail_flag to create or update resources in Shellgate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shellgate environment.
This tool modifies email flags/metadata without deleting or moving messages (those would be separate operations). Flag changes are reversible—flags can be set and unset. The severity is medium because misuse could mark emails as read/archived incorrectly or alter email organization, but the impact is localized to email metadata and does not involve destructive deletion, financial transactions, or arbitrary code…
From the tool's definition Tool name 'mail_flag' and description 'Set or unset flags on an email' indicates modification of email metadata. Flags like '\Seen', '\Flagged' are email attributes that can be changed, which constitutes reversible write operations on email state.
Documented attack patterns abuse exactly the kind of access mail_flag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Shellgate, and nothing reaches the server without passing your rules. This is the rule we recommend for mail_flag:
{
"version": "1",
"default": "deny",
"tools": {
"mail_flag": {
"limits": [
{
"counter": "mail_flag_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mail_flag 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.
Set or unset flags on an email (e.g. \\\\Seen, \\\\Flagged). It is categorised as a Write tool in the Shellgate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shellgate MCP server in PolicyLayer and add a rule for mail_flag: 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 Shellgate. Nothing to install.
mail_flag 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 mail_flag 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 mail_flag. 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.
mail_flag is provided by the Shellgate MCP server (matthiastjong/shellgate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Shellgate, 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.
31 Shellgate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.