MCP For Claude Marketplace
Tuputech Moderation

Tuputech Moderation MCP Connector for Claude

A+

Bring Tuputech's Advanced Anti-Spam and AI Evaluation endpoints to your server. Scan text, images, and audio automatically via AI.

10 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Integrate your AI closely with Tuputech (图普科技), one of the internet's most accurate machine-learning visual and text evaluation databases. With 10 deep scanning endpoints, you can create automated trust and safety AI workflows.

What you can do

  • Deepfake Detection — Submit image URLs directly to identify if they are AI-generated (Synthetic)
  • Categorical Risk Scoring — Split your moderation into Pornography, Terrorism, Toxic/Abuse, or Advertisement scanning intelligently depending on LLM context
  • A/V Streams — Trigger asynchronous moderation on videos or audio fragments rapidly

How it works

  1. Install this MCP Server
  2. Obtain an Access Key (SecretId) and generate your RSA Private Key from the Tuputech Developer Console
  3. Input them into the MCP server dynamically. Vurb perfectly crafts the underlying RSA Hash internally to avoid the LLM from executing crypto logic themselves.

Who is this for?

  • Discord / Community Bots — Have an LLM automatically check community links inside Tuputech's API
  • Platform Enforcers — Filter spam out of application comments effortlessly
  • Live App Managers — Intercept NSFW avatars uploaded via HTTP swiftly before reaching CDNs
content-moderationdeepfake-detectionanti-spamvisual-recognitiontrust-and-safety

10 tools expose this connector's capabilities to your AI agent.

scan_image_synthetic

Detect if an image is generated by AI (Deepfakes)

scan_image_terrorism

Scan an image for terrorism or gore

scan_text_abuse

Detect abusive or toxic language

submit_feedback

Submit manual feedback to improve AI results

scan_text_politics

Check if text violates strict political guidelines

scan_text_spam

Scan text block for spam and advertisements

scan_audio_stream

Initiate an asynchronous audio scan

scan_image_ad

Detect advertisements disguised inside images

scan_image_porn

Scan an image for NSFW or pornographic content

scan_video_stream

Initiate an asynchronous video scan

See how to talk to your AI agent using Tuputech Moderation.

Check if this profile photo contains NSFW or Gore imagery: https://...

I issued queries to both `scan_image_porn` and `scan_image_terrorism`. The photo passed all safety thresholds successfully with a 99% confidence score.

Scan this text and see if it is spam or political botting: 'Buy followers here...'

I dispatched the string to Tuputech. It returned a 'Reject' flag, labeling the content strictly under 'Spam/Fraud'.

No manual prompt instructions are needed. You simply set your RSA Private Key safely into your MCP profile in Vurb. When your AI triggers an endpoint like `scan_image_porn`, the Vurb NodeJS shell dynamically computes the RSA `signature` hashing your exact Nonce+Timestamp completely isolated from your prompt traces.

Related Connectors

OOPSpam

OOPSpam MCP

12 tools Official

Block spam submissions on your forms and comments with an AI-powered filter that catches bots without annoying real users.

A+ View details →
Voice Search Optimization Analyzer

Voice Search Optimization Analyzer MCP

4 tools Official

Analyze content for featured snippet and voice search suitability.

A+ View details →
Prompt Entropy and Clarity Scorer

Prompt Entropy and Clarity Scorer MCP

3 tools Official

A mathematical diagnostic tool to measure prompt complexity and cognitive load.

A+ View details →
Cognitive Load Scorer

Cognitive Load Scorer MCP

3 tools Official

Quantify the mental effort required to process text by measuring linguistic complexity.

A+ View details →