Content Moderation API

AI-powered content moderation for your agents. Detect spam, toxicity, PII, profanity, and NSFW content in one call. No paid API keys needed — rule-based and free.

Subscribe $19/mo →
🛡️

Spam Detection

Detect spam, scams, crypto giveaways, repeated phrases, and all-caps spam with pattern matching.

⚠️

Toxicity Check

Identify hate speech, harassment, self-harm content, and toxic language with comprehensive regex rules.

🔒

PII Redaction

Detect emails, phone numbers, SSNs, credit cards, IPs, crypto addresses, and API keys with masked output.

🤬

Profanity Filter

Comprehensive profanity detection with leetspeak variants and fuzzy matching patterns.

🖼️

Image Analysis

NSFW detection via pixel heuristics, dimension analysis, and image fingerprinting. Free tier included.

📊

Detailed Reports

Each moderation returns severity levels, matched patterns, match counts, and overall safety assessment.

Free

$0 /mo
  • 50 moderation calls
  • Text & image moderation
  • All detection types
  • Rate-limited per restart
Get Started →

Pro

$19 /mo
  • Unlimited moderation calls
  • Text & image moderation
  • Priority support
  • NEW Dedicated pro key
Subscribe →

Quick Start

# Install
pip install mcp anyio

# Run (free tier — 50 calls)
python3 server.py

# Run (pro tier — unlimited)
python3 server.py --pro-key PROL_AGENTPAY_DEMO

MCP Tools

# moderate_text — Detect spam, toxicity, PII, profanity
{
  "text": "Check this text for issues",
  "check_types": ["spam", "toxicity", "pii"]
}

# moderate_image — NSFW detection via heuristics
{
  "image_data": "<base64_encoded_image>"
}

# get_moderation_stats — Check usage and tier
{}