Get top-level comments. order: time|relevance. Cost: 1 unit per call.
AI agents call get_video_comments to retrieve information from SergeyKrin9/mcp Servers without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries comment data without modifying, deleting, or executing any operations. It has no side effects on the underlying data or systems. The low severity reflects minimal blast radius if misused—an AI agent could retrieve comments but cannot harm systems, delete data, or cause financial impact.
From the tool's definition Tool name is 'get_video_comments' and description states 'Get top-level comments' with ordering options (time|relevance).
Attacks that exploit this kind of access
Get top-level comments. order: time|relevance. Cost: 1 unit per call. It is categorised as a Read tool in the SergeyKrin9/mcp Servers MCP Server, which means it retrieves data without modifying state.
Register the SergeyKrin9/mcp Servers MCP server in PolicyLayer and add a rule for get_video_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 SergeyKrin9/mcp Servers. Nothing to install.
get_video_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 get_video_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 get_video_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.
get_video_comments is provided by the SergeyKrin9/mcp Servers MCP server (sergeykrin9/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →