Can I use this for user comments?

It's perfect for comments because it cleans the HTML while keeping safe tags like or intact.

Is it better than just asking an AI to clean the text?

Yes, because LLMs can't see how code actually renders, while this tool uses a real engine to catch hidden XSS vectors.

What happens to the safe parts of my HTML?

Tags on the whitelist are kept exactly as they are, while everything else gets removed.

Does it work on Base64 encoded scripts?

It's designed to catch many common obfuscation techniques that standard text filters miss.

How does it protect my database?

It cleans the data before it's saved, so your database never stores malicious payloads in the first place.

By default, it removes unsafe styles but leaves the structure intact.

Is it better than asking the LLM to do it?

Absolutely. LLMs are easily bypassed by obfuscated XSS payloads. This engine relies on strict deterministic whitelisting.

Sanitize HTML Connector for AI agents.

Q: Does the HTML XSS Sanitizer MCP stop scripts?

Yes, it strips out tags and other dangerous elements like to prevent them from running in a browser.

1 live capability

Protect your web application from cross-site scripting attacks by scrubbing user input.

Live agent request Sanitize HTML / Connector

Waiting for input…

AI Agent

Why people use Sanitize HTML

HTML XSS Sanitizer for Web Security: Stopping XSS in your database

This Connector changes that by putting a hard filter between your user and your database. When your agent handles a submission, it sends the raw HTML through the sanitizer first. It strips out the junk and keeps the safe parts. You get a clean string every time, so you don't have to worry about your site getting hijacked by a malicious script.

What Vinkius changes

That your AI agent can handle raw user input without risking a security breach.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 6,100+ Connectors

Real-world use case 01

Cleaning forum comments

A user submits a comment with a hidden script.
Real-world use case 02

Sanitizing profile bios

Someone tries to inject an iframe into their bio.
Real-world use case 03

Safe blog content

An editor pastes a messy HTML snippet.

Complete set · 1capability

The complete Sanitize HTML capability set.

These are the exact actions your AI can choose when you ask it to work with Sanitize HTML.

Capability set01 / 01

01

1 capability in this set.

Part of 1 available through Sanitize HTML.

01 Capability
SanitizeHtml html
Strips malicious XSS vectors and unsafe tags from HTML payloads before they are saved to a database. This ensures your data stays clean and safe for all users.

Set up in minutes

One URL. Then ask Sanitize HTML to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Sanitize HTML from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Sanitize HTML, and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Sanitize HTML for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Sanitize HTML URL.
Step 03

Save and start

Save the connection and enable Sanitize HTML in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "html-xss-sanitizer": {
      "url": "https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Sanitize HTML

Open Agent mode in chat and ask: "Using Sanitize HTML, help me...". 1 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "html-xss-sanitizer": {
      "url": "https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Sanitize HTML

Ask Copilot: "Using Sanitize HTML, help me...". 1 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "html-xss-sanitizer": {
      "url": "https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Sanitize HTML

Open Cascade and ask: "Using Sanitize HTML, help me...". 1 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "html-xss-sanitizer": {
      "url": "https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Sanitize HTML

Ask Cline: "Using Sanitize HTML, help me...". 1 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add html-xss-sanitizer --transport http "https://edge.vinkius.com/vk_preview_wOJVwhEm2CsSI6rmzlbp7pTP6UdMKdT328oW1l5P/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Sanitize HTML

Ask Claude: "Using Sanitize HTML, show me...". 1 tools are ready

Where the request belongs

Work Sanitize HTML can move forward.

Built around the request

This is for web developers and security engineers who deal with user-generated content. It's for anyone who needs to stop XSS attacks without manually reviewing every single submission.

Full-stack Developer

Cleans up user comments and forum posts before they go live in the production database.

Security Engineer

Automates the sanitization of data flowing into the backend to prevent injection attacks.

CMS Administrator

Ensures that blog posts and widgets don't contain malicious scripts that could hijack user sessions.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 3 capabilities

Regex Toolkit

Equip your AI with strict Regular Expressions. Deterministically extract, validate, and redact Emails, URLs, and Phones without hallucinations.

View Connector

02 1 capability

HTML to Text Extractor

Stop wasting AI context on messy HTML code. Instantly strip CSS, tags, and scripts to extract perfectly readable Plain Text.

View Connector

03 1 capability

Strict PII Redaction Engine

Instantly strip sensitive personal data from documents using deterministic, bulletproof regex patterns before AI processing.

View Connector

04 4 capabilities

Shumei Anti-Fraud

Bring Shumei's top-tier Anti-Fraud and Risk Control to your AI. Analyze text, images, and devices for malicious activity instantly.

View Connector

05 3 capabilities

Tool Output Entropy Sanitizer

Detects and redacts high-entropy strings like API keys from capability outputs.

View Connector

06 3 capabilities

Prompt Injection Pattern Detector

Detects malicious prompt injection attempts in LLM inputs using deterministic regex patterns.

View Connector

Bring your own AI

Change the model, client or framework. Keep Sanitize HTML connected.

Claude
ChatGPT
Gemini
Cursor
VS Code
Windsurf
ZCode
Cline
Zed
Continue
Kiro
Roo Code
Zencoder
Goose
Void
Augment Code
Amp
Qodo
Tabnine
Pieces
Sourcegraph Cody
JetBrains
Warp
Amazon Q
Antigravity
BoltAI
Raycast
Jan
LM Studio
AnythingLLM
Open WebUI
Msty
Cherry Studio
LibreChat
TypingMind
Chorus
5ire
n8n
LangChain
LlamaIndex
CrewAI
Vercel AI SDK

Before you connect

Questions about Sanitize HTML.

The practical details behind the request, access and result.

Does the HTML XSS Sanitizer MCP stop scripts?

Yes, it strips out

HTML XSS Sanitizer for Web Security: Stopping XSS in your database

That your AI agent can handle raw user input without risking a security breach.

Cleaning forum comments

Sanitizing profile bios

Safe blog content

SanitizeHtml html

Open Connectors

Add the URL

Turn it on in chat

Open MCP settings

Add the URL

Save and start

Open MCP Settings

Add the server config

Save the file

Start using Sanitize HTML

Create MCP config

Add the server config

Enable Agent mode

Start using Sanitize HTML

Open MCP Settings

Add the server

Save and reload

Start using Sanitize HTML

Open Cline MCP Settings

Add remote server

Enable the server

Start using Sanitize HTML

Install Claude Code

Add the Connector

Verify the connection

Start using Sanitize HTML

Full-stack Developer

Security Engineer

CMS Administrator

Regex Toolkit

HTML to Text Extractor

Strict PII Redaction Engine

Shumei Anti-Fraud

Tool Output Entropy Sanitizer

Prompt Injection Pattern Detector