AI agents use youtube_set_comment_moderation to create or update resources in Youtube — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Youtube environment.
While this tool modifies data and has user-facing consequences (banning authors), it falls into the Write category because: (1) it modifies existing comments and user permissions rather than deleting them irreversibly, (2) these changes are generally reversible, and (3) it does not move money, execute arbitrary code, or permanently destroy data.
From the tool's definition Tool description states it 'Sets the moderation status of one or more comments' and 'Can optionally ban the comment author(s)'.
Attacks that exploit this kind of access
Sets the moderation status of one or more comments. Can optionally ban the comment author(s). Args - \. It is categorised as a Write tool in the Youtube MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Youtube MCP server in PolicyLayer and add a rule for youtube_set_comment_moderation: 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 Youtube. Nothing to install.
youtube_set_comment_moderation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the youtube_set_comment_moderation 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 youtube_set_comment_moderation. 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.
youtube_set_comment_moderation is provided by the Youtube MCP server (tuitamogamer-gpt/youtube-mcp-server). 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 →