AI agents invoke kupid_login to trigger actions in Ku Portal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool initiates an authenticated session with an external portal system. It triggers an external operation (authentication) whose effects (session creation, credential transmission) depend on the supplied arguments. Misuse could expose student credentials or create unauthorized sessions, warranting high severity. It is not purely a read operation since it creates a session state on the remote system.
From the tool's definition KUPID 포털에 로그인하고 세션을 확인합니다 — logs into the KUPID portal and establishes/verifies a session
Documented attack patterns abuse exactly the kind of access kupid_login gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ku Portal, and nothing reaches the server without passing your rules. This is the rule we recommend for kupid_login:
{
"version": "1",
"default": "deny",
"tools": {
"kupid_login": {
"limits": [
{
"counter": "kupid_login_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}kupid_login stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
KUPID 포털에 로그인하고 세션을 확인합니다. It is categorised as a Execute tool in the Ku Portal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ku Portal MCP server in PolicyLayer and add a rule for kupid_login: 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 Ku Portal. Nothing to install.
kupid_login is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kupid_login 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 kupid_login. 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.
kupid_login is provided by the Ku Portal MCP server (sonaiengine/ku-portal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ku Portal, 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 Ku Portal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.