AI agents call parse_xhs_link to retrieve information from Wanyi Watermark Remover without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server description and naming convention (similar to 'parse_douyin_link' sibling tool), this tool likely parses/fetches content from Xiaohongshu share links, which is a Read operation. Severity is medium because it involves fetching external content and potentially bypassing watermark protections. Confidence is reduced due to empty tool description.
From the tool's definition Tool name 'parse_xhs_link' and server context: 'Extracts watermark-free videos and images from Xiaohongshu (RedNote) share links'
Documented attack patterns abuse exactly the kind of access parse_xhs_link gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wanyi Watermark Remover, and nothing reaches the server without passing your rules. This is the rule we recommend for parse_xhs_link:
{
"version": "1",
"default": "deny",
"tools": {
"parse_xhs_link": {}
}
}parse_xhs_link 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.
parse_xhs_link. It is categorised as a Read tool in the Wanyi Watermark Remover MCP Server, which means it retrieves data without modifying state.
Register the Wanyi Watermark Remover MCP server in PolicyLayer and add a rule for parse_xhs_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 Wanyi Watermark Remover. Nothing to install.
parse_xhs_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 parse_xhs_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 parse_xhs_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.
parse_xhs_link is provided by the Wanyi Watermark Remover MCP server (ryan7t/wanyi-watermark). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wanyi Watermark Remover, 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.
4 Wanyi Watermark Remover tools catalogued and risk-classified — across an index of 43,000+ MCP servers.