AI agents call parse_douyin_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 context, this tool likely fetches/parses a Douyin share link to retrieve media content (videos/images) without watermarks. This is a read/fetch operation with no apparent write or destructive side effects. Confidence is reduced due to the empty tool description. Severity is medium because it involves downloading and processing third-party media content, which may raise copyright or ToS concerns.
From the tool's definition Tool name 'parse_douyin_link' and server description mentions extracting watermark-free videos and images from Douyin share links; description is empty.
Documented attack patterns abuse exactly the kind of access parse_douyin_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_douyin_link:
{
"version": "1",
"default": "deny",
"tools": {
"parse_douyin_link": {}
}
}parse_douyin_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_douyin_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_douyin_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_douyin_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_douyin_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_douyin_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_douyin_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.