通过验证码的方式登录小红书账号，当不带验证码的方式登录小红书账号失败时使用
AI agents use login_with_verification_code to create or update resources in Xhs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xhs environment.
This tool authenticates/logs into a Xiaohongshu account using a verification code. It creates a session state (authentication session), which is a reversible Write operation. Misuse could allow unauthorized account access, but it doesn't directly delete data or move money. Severity is medium because it grants account access which could enable further harmful actions.
From the tool's definition 登录小红书账号 (login to Xiaohongshu account) using verification code
Documented attack patterns abuse exactly the kind of access login_with_verification_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xhs, and nothing reaches the server without passing your rules. This is the rule we recommend for login_with_verification_code:
{
"version": "1",
"default": "deny",
"tools": {
"login_with_verification_code": {
"limits": [
{
"counter": "login_with_verification_code_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}login_with_verification_code 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.
通过验证码的方式登录小红书账号，当不带验证码的方式登录小红书账号失败时使用. It is categorised as a Write tool in the Xhs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xhs MCP server in PolicyLayer and add a rule for login_with_verification_code: 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 Xhs. Nothing to install.
login_with_verification_code 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 login_with_verification_code 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 login_with_verification_code. 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.
login_with_verification_code is provided by the Xhs MCP server (softegli/xhs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xhs, 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.
3 Xhs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.