Multi-language UGC content moderation for marketplaces, social platforms and comment systems. Detects policy violations in text content across 9 policies and 12 languages without external API calls. Policies checked: • hate — hate speech, slurs, dehumanization (50+ terms × 12 languages) • sexual ...
Risk signalsAccepts raw HTML/template content (content)
Part of the Mcp Knowledge server.
Free to start. No card required.
AI agents use ugc_moderation_classifier to create or modify resources in Mcp Knowledge. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call ugc_moderation_classifier repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Mcp Knowledge.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"ugc_moderation_classifier": {
"limits": [
{
"counter": "ugc_moderation_classifier_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Mcp Knowledge policy for all 271 tools.
These attack patterns abuse exactly the kind of access ugc_moderation_classifier gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Multi-language UGC content moderation for marketplaces, social platforms and comment systems. Detects policy violations in text content across 9 policies and 12 languages without external API calls. Policies checked: • hate — hate speech, slurs, dehumanization (50+ terms × 12 languages) • sexual — explicit sexual content, pornography references, nudity solicitation • violence — threats, weapon references, graphic violence • self_harm — suicidal ideation, self-injury, eating disorder promotion • harassment — doxxing, stalking, cyberbullying, blackmail • scam — phishing, investment fraud, romance scam, lottery fraud • spam — bots, keyword stuffing, excessive caps, emoji storms, suspicious URLs • copyright — piracy, leaked content, serial keys, streaming fraud • minor_safety — grooming signals, CSAM references, minor + adult content combos Languages: en / fr / de / es / it / pt / nl / zh / ja / ko / ar / ru (auto-detected) Output includes severity (low/medium/high/severe), confidence (0-100), matched patterns, excerpt, recommended action, age appropriateness (adult/teen/child), and signals. No API key required. Stateless — no content is stored or logged.. It is categorised as a Write tool in the Mcp Knowledge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for ugc_moderation_classifier: 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 Knowledge. Nothing to install.
ugc_moderation_classifier 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 ugc_moderation_classifier 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 ugc_moderation_classifier. 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.
ugc_moderation_classifier is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 271 Mcp Knowledge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.