访问知乎登陆页面,并获取二维码。
AI agents invoke login-with-qrcode to trigger actions in zhihu MCP Server. 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 triggers an external browser action via Puppeteer to navigate to the Zhihu login page and retrieve a QR code. It executes a browser-driven operation with external side effects (opening a browser session, initiating an authentication flow), placing it in the Execute category.
From the tool's definition 访问知乎登陆页面,并获取二维码 (Access Zhihu login page and obtain QR code); server description mentions 'Puppeteer with QR code login authentication'
Attacks that exploit this kind of access
访问知乎登陆页面,并获取二维码。. It is categorised as a Execute tool in the zhihu MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the zhihu MCP Server MCP server in PolicyLayer and add a rule for login-with-qrcode: 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 zhihu MCP Server. Nothing to install.
login-with-qrcode 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 login-with-qrcode 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-qrcode. 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-qrcode is provided by the zhihu MCP Server MCP server (morrain/zhihumcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →