# Moderation API (moderationapi.com)

Detects and reviews harmful text, images, video and audio via API, applying custom rules and a human review queue.

- Atlas card: https://inite.ai/en/atlas/moderationapi.com
- Site: https://moderationapi.com
- For: trust and safety teams at companies moderating user-posted text, images, video and audio
- Categories: security
- Use not measured/100 · alive 100/100

## Used for

- detect spam and scam links in user messages
- review flagged content in a moderation queue
- block or auto-approve posts using custom if-then rules

## Price

- freemium, free plan (read 2026-10-29 on https://moderationapi.com/pricing)

## For developers

- API docs: https://docs.moderationapi.com/api-reference
- MCP server: com.moderationapi/moderation-api (namespace; auth on 2026-10-29)
- Status page: https://stats.uptimerobot.com/jJKn6IjEKD
- Read 2026-10-29

## MCP server, measured daily

Server: https://mcp.moderationapi.com/mcp, checked every day since 2026-10-30 (3 checks).

- Answered: measuring, 3 daily checks so far
- Median first answer: 206 ms
- Sign-in: OAuth (the client signs the user in)
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: ccpa, gdpr
- Read 2026-10-29

---

Source: INITE Atlas, https://inite.ai/en/atlas/moderationapi.com. JSON: https://inite.ai/api/atlas/moderationapi.com. MCP: https://inite.ai/api/mcp (atlas_lookup).