Send an email. Requires approval — first call returns approval_required, re-call with approved: true after user confirms.
AI agents use mail_send 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.
mail_send creates and sends emails, which are write operations that modify state (a new message exists in recipients' inboxes) but are theoretically reversible (delete/recall, though imperfect). It does not execute arbitrary code, delete data irreversibly, or move money, so it does not qualify as Execute, Destructive, or Financial.
From the tool's definition Tool name: mail_send. Description states 'Send an email' — this creates and transmits a message, a reversible write action.
Documented attack patterns abuse exactly the kind of access mail_send 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_send:
{
"version": "1",
"default": "deny",
"tools": {
"mail_send": {
"limits": [
{
"counter": "mail_send_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mail_send 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.
Send an email. Requires approval — first call returns approval_required, re-call with approved: true after user confirms. 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_send: 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_send 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_send 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_send. 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_send 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.