支持无密码与带密码分享页；自动提取 /fn 或分享页脚本中的 ajaxm/sign，并请求 downprocess 获取直链。
AI agents call lanzou_get_direct_link to retrieve information from Lanzou MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves direct download links from Lanzou Cloud storage pages (with or without passwords). It parses existing share pages and extracts link information via API requests, but does not create, modify, delete, or execute arbitrary code.
From the tool's definition Tool description indicates it 'extracts...and requests downprocess to get direct link' — this is information retrieval and parsing of download links.
Attacks that exploit this kind of access
支持无密码与带密码分享页；自动提取 /fn 或分享页脚本中的 ajaxm/sign，并请求 downprocess 获取直链。. It is categorised as a Read tool in the Lanzou MCP MCP Server, which means it retrieves data without modifying state.
Register the Lanzou MCP server in PolicyLayer and add a rule for lanzou_get_direct_link: 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 Lanzou MCP. Nothing to install.
lanzou_get_direct_link 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 lanzou_get_direct_link 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 lanzou_get_direct_link. 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.
lanzou_get_direct_link is provided by the Lanzou MCP server (k0itoyuu/lanzou-mcp). 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 →