How does the MCP handle security?

The MCP handles the RSA hashing internally. This prevents your AI client from needing to execute complex crypto logic itself.

What kind of media can I scan?

You can scan text, images, audio fragments, and video streams.

Can I use this for deepfake detection?

Yes, you can use the scan_image_synthetic capability to identify if an image is AI-generated.

Does it support video moderation?

Yes, the scan_video_stream capability allows for asynchronous video scanning.

Which AI clients can use this?

You can use this MCP with any compatible client like Claude, Cursor, or Windsurf.

How is the RSA authentication performed?

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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Tuputech Moderation to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Automate trust and safety workflows with deep machine learning scans.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Tuputech.

01
Scan image synthetic
This capability identifies if an image was created by AI. Use it to catch deepfakes and synthetic media.
02
Scan image terrorism
This capability scans images for gore or terrorist content. It's built for high-stakes safety filtering.
03
Scan text abuse
This capability detects abusive or toxic language in text. Use it to keep chat logs clean.
04
Submit feedback
This capability sends manual feedback to the Tuputech system. It helps refine the accuracy of the machine learning models.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Tuputech.

05
Scan text politics
This capability checks text against strict political guidelines. Use it to flag sensitive political content.
06
Scan text spam
This capability scans text blocks for advertisements and spam. It's useful for filtering bot comments.
07
Scan audio stream
This capability starts an asynchronous scan of audio files. It works well for monitoring voice data.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Tuputech.

08
Scan image ad
This capability detects advertisements hidden within images. Use it to catch sneaky marketing content.
09
Scan image porn
This capability scans images for pornographic or NSFW content. It helps prevent inappropriate uploads.
10
Scan video stream
This capability initiates an asynchronous scan of video content. It allows for rapid moderation of video streams.

Real work

What teams actually run

Community Moderation

An agent automatically scans user-uploaded profile pictures for NSFW content.

Spam Prevention

The agent flags suspicious text comments that look like advertisements or bot activity.

Deepfake Verification

You use the agent to check if a suspicious image is a synthetic deepfake.

Media Stream Safety

An agent monitors video and audio streams for prohibited content in real time.

Automate a task

Put Tuputech to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Tuputech works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Tuputech to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

922ms average. Fast in production.

Tuputech is checked daily against the live service.

Daily averagePeak 1039ms

Oct 3Today

Fastest day: 771ms
Slowest day: 1039ms
14-day trend: Slowing+17%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Tuputech, so you can see the experience inside your AI.

It does not authenticate your account with Tuputech. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Tuputech Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_gb0XPkdhb9Za66CEymV09DgwDJyFdD3cFgotR1xY/mcp

Claude 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.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "tuputech-moderation-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_gb0XPkdhb9Za66CEymV09DgwDJyFdD3cFgotR1xY/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Tuputech in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Tuputech owners hand off.

This MCP is built for developers and operators who need to automate content safety at scale.

01
Discord Bot Developers
They hand off link and image scanning to the agent to keep communities safe.
02
Platform Enforcers
They use the agent to filter spam and toxic comments from application feeds.
03
Live App Managers
They task the agent with intercepting NSFW uploads before they reach the CDN.

FAQ

Questions Tuputech owners ask.

01
How does the MCP handle security?
The MCP handles the RSA hashing internally. This prevents your AI client from needing to execute complex crypto logic itself.
02
What kind of media can I scan?
You can scan text, images, audio fragments, and video streams.
03
Can I use this for deepfake detection?
Yes, you can use the scan_image_synthetic capability to identify if an image is AI-generated.
04
Does it support video moderation?
Yes, the scan_video_stream capability allows for asynchronous video scanning.
05
Which AI clients can use this?
You can use this MCP with any compatible client like Claude, Cursor, or Windsurf.
06
How is the RSA authentication performed?
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.

Explore

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Scan image synthetic

Scan image terrorism

Scan text abuse

Submit feedback

05-07

Scan text politics

Scan text spam

Scan audio stream

08-10

Scan image ad

Scan image porn

Scan video stream

What teams actually run

Community Moderation

Spam Prevention

Deepfake Verification

Media Stream Safety

Building your own app? The connector is yours to use.

Tuputech Connector

Claude Desktop

Discord Bot Developers

Platform Enforcers

Live App Managers

How does the MCP handle security?

What kind of media can I scan?

Can I use this for deepfake detection?

Does it support video moderation?

Which AI clients can use this?

How is the RSA authentication performed?

Shumei Anti-Fraud AI Connector

MarketMuse (AI Content Strategy & SEO) AI Connector

Hive AI AI Connector

OOPSpam AI Connector

Suggestions

Contentful AI Connector

Contentdrips AI Connector

Accelerator Anti-Dilution Protection AI Connector

Venture Anti-Dilution Protection Analysis AI Connector