Content moderation. POST { text }. Flags content across categories — hate, harassment, sexual, sexual/minors, violence, self-harm, dangerous, illicit — with a per-category boolean and 0..1 severity score, plus an overall flagged verdict. For UGC filtering, trust & safety, and pre-publish checks.
AI agents call ai.moderate to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and classifies user-provided content to determine policy violations, returning categorized flags and severity scores. It performs content inspection and assessment—a pure read/analysis operation with no side effects on data, systems, or financial state. While the moderation result may inform downstream actions by a host system, the tool itself only reads input and returns classification output.
From the tool's definition Tool description states it 'Flags content across categories' and 'with a per-category boolean and 0..1 severity score, plus an overall flagged verdict.' The input is text data and the output is classification/moderation results.
Attacks that exploit this kind of access
Content moderation. POST { text }. Flags content across categories — hate, harassment, sexual, sexual/minors, violence, self-harm, dangerous, illicit — with a per-category boolean and 0..1 severity score, plus an overall flagged verdict. For UGC filtering, trust & safety, and pre-publish checks. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for ai.moderate: 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 Mcp. Nothing to install.
ai.moderate 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 ai.moderate 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 ai.moderate. 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.
ai.moderate is provided by the MCP server (@2sio/mcp). 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 →