AI agents call crawler_comments to retrieve information from MediaCrawler MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts comments from public videos on Bilibili, a Chinese video platform. It performs a GET-like operation that queries existing data without modifying, deleting, or executing code. The operation is read-only and has no side effects on the platform or user data.
From the tool's definition Tool name 'crawler_comments' and description '按视频 ID 抓取 Bilibili 评论' (fetch Bilibili comments by video ID) indicates retrieval of public comment data with no modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access crawler_comments gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MediaCrawler MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for crawler_comments:
{
"version": "1",
"default": "deny",
"tools": {
"crawler_comments": {}
}
}crawler_comments 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.
按视频 ID 抓取 Bilibili 评论. It is categorised as a Read tool in the MediaCrawler MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MediaCrawler MCP Server MCP server in PolicyLayer and add a rule for crawler_comments: 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 MediaCrawler MCP Server. Nothing to install.
crawler_comments 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 crawler_comments 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 crawler_comments. 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.
crawler_comments is provided by the MediaCrawler MCP Server MCP server (mcp-service/media-crawler-mcp-service). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MediaCrawler MCP Server, 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.
5 MediaCrawler MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.