NAVER WORKS 메일을 전송합니다.
AI agents use nworks_mail_send to create or update resources in Nworks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nworks environment.
Sending mail is a Write operation that creates new email messages and delivers them to recipients. While reversible in some systems (unsend features exist), the primary effect is to create and transmit data with real-world consequences (reaching external parties).
From the tool's definition Tool name 'nworks_mail_send' and description '메일을 전송합니다' (sends mail) directly indicates the tool creates and transmits email messages.
Documented attack patterns abuse exactly the kind of access nworks_mail_send gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nworks, and nothing reaches the server without passing your rules. This is the rule we recommend for nworks_mail_send:
{
"version": "1",
"default": "deny",
"tools": {
"nworks_mail_send": {
"limits": [
{
"counter": "nworks_mail_send_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}nworks_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.
NAVER WORKS 메일을 전송합니다. It is categorised as a Write tool in the Nworks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nworks MCP server in PolicyLayer and add a rule for nworks_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 Nworks. Nothing to install.
nworks_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 nworks_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 nworks_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.
nworks_mail_send is provided by the Nworks MCP server (yjcho9317/nworks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nworks, 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.
26 Nworks tools catalogued and risk-classified — across an index of 43,000+ MCP servers.