AI agents call search_bilibili_videos to retrieve information from Bilibili Subtitle Fetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name combined with server context indicates this searches for videos without modifying or deleting data. The blast radius is low—misuse would retrieve video metadata or links, not compromise systems or trigger irreversible actions. Confidence is moderate (0.75) due to missing tool description.
From the tool's definition Tool name 'search_bilibili_videos' indicates a search operation. Server description states it 'supports various input formats' and 'fetches' subtitles, suggesting data retrieval capability.
Documented attack patterns abuse exactly the kind of access search_bilibili_videos gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bilibili Subtitle Fetch, and nothing reaches the server without passing your rules. This is the rule we recommend for search_bilibili_videos:
{
"version": "1",
"default": "deny",
"tools": {
"search_bilibili_videos": {}
}
} search_bilibili_videos 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.
search_bilibili_videos. It is categorised as a Read tool in the Bilibili Subtitle Fetch MCP Server, which means it retrieves data without modifying state.
Register the Bilibili Subtitle Fetch MCP server in PolicyLayer and add a rule for search_bilibili_videos: 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 Bilibili Subtitle Fetch. Nothing to install.
search_bilibili_videos 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 search_bilibili_videos 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 search_bilibili_videos. 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.
search_bilibili_videos is provided by the Bilibili Subtitle Fetch MCP server (initsnow/bilibili-subtitle-fetch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bilibili Subtitle Fetch, 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 Bilibili Subtitle Fetch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.