특정 메일의 상세 내용(본문, 첨부파일 등)을 조회합니다.
AI agents call nworks_mail_read to retrieve information from Nworks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email content without modifying, deleting, or executing any operations. It is a read-only query that accesses existing data. The severity is low because email reading, while sensitive from a privacy perspective, does not cause irreversible changes or execute arbitrary code.
From the tool's definition Tool name contains 'read' and description states '특정 메일의 상세 내용(본문, 첨부파일 등)을 조회합니다' which translates to 'retrieves detailed content (body, attachments, etc.) of a specific email'. The verb '조회' (joohoe) means 'to query' or 'retrieve'.
Documented attack patterns abuse exactly the kind of access nworks_mail_read 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_read:
{
"version": "1",
"default": "deny",
"tools": {
"nworks_mail_read": {}
}
}nworks_mail_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
특정 메일의 상세 내용(본문, 첨부파일 등)을 조회합니다. It is categorised as a Read tool in the Nworks MCP Server, which means it retrieves data without modifying state.
Register the Nworks MCP server in PolicyLayer and add a rule for nworks_mail_read: 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_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the nworks_mail_read 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_read. 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_read 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.