Get danmaku (bullet comments) from a Bilibili video
AI agents call get_danmaku to retrieve information from Bilibili Video Info MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query/retrieval operation on existing video data (danmaku/bullet comments) with no side effects, data modification, or destructive actions. It is a straightforward data retrieval function that fits the Read category. Severity is low because retrieving public comment data from a video platform carries minimal risk of harm from misuse.
From the tool's definition Tool retrieves danmaku (bullet comments) from videos using video URL. Description states 'Get danmaku' with no modification, deletion, or execution capabilities. Sibling tools are get_comments and get_subtitles, all following a read-only pattern.
Documented attack patterns abuse exactly the kind of access get_danmaku gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bilibili Video Info MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_danmaku:
{
"version": "1",
"default": "deny",
"tools": {
"get_danmaku": {}
}
}get_danmaku 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.
Get danmaku (bullet comments) from a Bilibili video. It is categorised as a Read tool in the Bilibili Video Info MCP MCP Server, which means it retrieves data without modifying state.
Register the Bilibili Video Info MCP server in PolicyLayer and add a rule for get_danmaku: 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 Video Info MCP. Nothing to install.
get_danmaku 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 get_danmaku 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 get_danmaku. 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.
get_danmaku is provided by the Bilibili Video Info MCP server (lesir831/bilibili-video-info-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bilibili Video Info MCP, 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 Video Info MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.