- SYNTHETIC
- NSFW
- ADVERT
- HUMAN
Short answer
How can I use my AI to find deepfakes and NSFW images?
Your AI uses specific scanning tools to identify synthetic media and inappropriate visuals. It flags these issues immediately so you can decide how to handle them. You get a clear breakdown of what was found in every scan.
Where every issue lands.
Automated moderation outcomes
The AI sorts every image it scans into one of these four categories.
SYNTHETIC
Deepfake detection
The AI identifies images that were generated by other AI models. You get a warning that the media is not authentic.
NSFW
Inappropriate content
The AI catches pornographic or explicit imagery. This keeps your platform clean without manual browsing.
ADVERT
Marketing check
The AI flags images that look like advertisements. This helps you manage commercial content in your feed.
HUMAN
Manual review needed
If the AI is unsure about a specific image, it flags it for you. You make the final call on borderline cases.
The workflow
What your AI does when an image arrives.
Your agent acts as a gatekeeper for every visual upload.
Check for AI generation
The AI looks for patterns that indicate an image is synthetic rather than real.
scan_image_syntheticFilter explicit content
The agent scans the visual data for pornographic material.
scan_image_pornIdentify commercial ads
The AI detects if an image is an advertisement.
scan_image_adReport findings
The agent summarizes the scan results and presents the risk level to you.
scan_image_syntheticscan_image_pornscan_image_ad
Try it
Copy these to start.
Use these prompts to trigger the moderation tools.
Starting points
These are basic ways to start. Swap out the specific channel or file names for your own.
Tuputech Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_gb0XPkdhb9Za66CEymV09DgwDJyFdD3cFgotR1xY/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Tuputech capabilities are ready to use.
{
"mcpServers": {
"tuputech-moderation-mcp": {
"url": "https://edge.vinkius.com/vk_preview_gb0XPkdhb9Za66CEymV09DgwDJyFdD3cFgotR1xY/mcp"
}
}
}Scan the latest images in my #uploads channel for deepfakes.
Check this image file for any NSFW content.
Look through the images in my Google Drive folder and flag any ads.
Run a moderation check on the images I just uploaded to this repo.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Tuputech Moderation once, then ask.
You only need to link the MCP once. Your login credentials stay encrypted, and you can immediately start asking your AI to scan content.
Connect Tuputech Moderation to your AIFAQ
How this task behaves
- 01
Can the AI delete the NSFW images automatically?
No. The AI only identifies and flags the content. You must manually delete or manage the files yourself.
- 02
Does the AI scan video files too?
No. The current tools are specifically designed for image scanning.
- 03
Will the AI notify my users if an image is a deepfake?
No. The AI only reports the findings to you. It does not interact with your users or send them notifications.
- 04
Can the AI tell if an image is a high-quality professional photo?
No. The tools focus on detecting synthetic generation, pornographic content, and advertisements.
- 05
Does the AI store the images it scans?
No. The AI processes the images to perform the scan and does not keep a copy of the visual data.
More questions about Tuputech Moderation? The Connector page answers them. See everything the Tuputech Moderation Connector can do
Connect Tuputech to Claude, Cursor, ChatGPT & more
