How to Use the HTML XSS Sanitizer MCP in Vercel AI SDK

Q: How do I initialize this tool in my TypeScript project?

Install @ai-sdk/mcp and set up your MCP client using the HTTP transport. Pass the tool list to generateText or streamText to let your agent clean raw markup automatically.

Clean untrusted markup on the fly as your Vercel AI SDK app streams dynamic content directly to the browser.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HTML XSS Sanitizer MCP to Vercel AI SDK

Create your Vinkius account to connect HTML XSS Sanitizer to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup HTML XSS Sanitizer with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe streaming UI with Vercel AI SDK

The `sanitizeHtml_html` tool strips malicious scripts from raw text streams before they reach your user-facing UI. When your application streams AI-generated code snippets or user-submitted rich text, you risk executing malicious scripts in the user's browser. This MCP setup runs inside your Edge Functions. Because the parsing happens locally inside the sandbox, you do not need to make external API calls to clean the markup. Your users get the fast, interactive streaming experience they expect, completely safe from injected scripts.

Clean database writes from the Edge

The `sanitizeHtml_html` tool removes persistent script injections from user-submitted rich text before you write it to your database. Storing rich text directly from a client input is a massive security risk. By passing raw strings to this tool inside your Vercel AI SDK route handlers, you strip bad tags before they ever touch your database. This prevents persistent XSS attacks where one user's malicious payload runs in another user's session. It handles the cleanup instantly, allowing your database transactions to finish without waiting on slow external security APIs.

Zero-latency local sanitization

The `sanitizeHtml_html` tool processes raw markup locally inside a V8 isolate to eliminate network latency. Traditional security gateways add lag to your real-time applications. This MCP server handles HTML parsing locally, meaning it strips dangerous tags in milliseconds without network roundtrips. Your Vercel AI SDK agents can safely output rich-text formats like tables, lists, and links. The tool strips out `<script>` or `onload` vectors, leaving only the structural layout you actually want to render.

Setup guide

Set up HTML XSS Sanitizer MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all HTML XSS Sanitizer tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent HTML XSS Sanitizer transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sanitize HTML. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect HTML XSS Sanitizer now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about HTML XSS Sanitizer MCP in Vercel AI SDK

It processes raw text blocks as they stream from the model. By calling `sanitizeHtml_html` on your MCP connection before rendering, you strip out malicious tags like script or iframe on the fly. This keeps your live UI safe from DOM-based script execution.

Yes, the MCP server runs inside a lightweight V8 sandbox that is fully compatible with Edge runtimes. You just initialize the client using `createMCPClient` and invoke `sanitizeHtml_html` directly in your edge route.

No, because the cleanup happens locally without external network requests. The `sanitizeHtml_html` tool runs in milliseconds, meaning your streaming UI stays fast while keeping the output safe.

Install `@ai-sdk/mcp` and set up your MCP client using the HTTP transport. Pass the tool list to `generateText` or `streamText` to let your agent clean raw markup automatically.

Your HTML payloads never leave the local V8 sandbox. The server runs in an ephemeral, zero-trust environment that processes the text instantly and discards it immediately after returning the clean string.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript