How to Use the HTML DOM Query Engine MCP in Mastra AI

Q: How do I configure the HTML DOM Query Engine inside Mastra AI?

Install the package using npm install @mastra/mcp@latest to get the necessary client. Instantiate a new MCPClient with the server URL, then fetch the tools and pass them directly to your Mastra AI Agent instance.

Q: Can I use the HTML DOM Query Engine with Mastra AI's conditional steps?

Absolutely. You can run the querydom tool to check for specific elements, then use the returned text to branch your Mastra AI workflow. This allows you to handle different page layouts dynamically.

Build resilient, multi-step HTML parsing workflows with Mastra AI and deterministic DOM queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HTML DOM Query Engine MCP to Mastra AI

Create your Vinkius account to connect HTML DOM Query Engine to Mastra AI 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 DOM Query Engine with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Workflows with Mastra AI

The `query_dom` tool extracts specific text or attributes from raw HTML strings using standard CSS selectors. When integrated into a Mastra AI workflow as an MCP Server tool, this tool acts as a reliable step in your automation pipelines. You can easily feed the extracted DOM data into downstream tasks like database writes or notification loops. If the targeted website changes its structure, Mastra's built-in workflow engine handles the failure gracefully. You can write conditional logic to retry with alternative selectors or alert your engineering team immediately.

Conditional Branching Based on CSS Selectors

The `query_dom` tool allows your agent to inspect specific HTML structures and make immediate routing decisions. Within Mastra AI, you can branch your workflow depending on whether a CSS selector finds an element. For example, if a price element is missing, your agent can route the payload to a fallback parsing step. This programmatic control prevents your workflows from stalling on malformed markup. You build robust scraping pipelines that handle edge cases without human intervention.

Human-in-the-Loop Approvals for DOM Queries

The `query_dom` tool can be gated behind human approval before it executes inside your Mastra AI agent. This is particularly useful when parsing high-value HTML payloads where accuracy is critical. You can review the incoming HTML and the target CSS selector before letting the agent run the tool. Setting this up requires just a simple configuration flag in your agent initialization. It gives you complete control over automated data extraction tasks.

Setup guide

Set up HTML DOM Query Engine MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All HTML DOM Query Engine tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "html-dom-query-engine-mcp-client",
  servers: {
    "html-dom-query-engine-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "HTML DOM Query Engine Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to HTML DOM Query Engine tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent HTML DOM Query Engine transactions"
);
console.log(result.text);

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 Cheerio DOM. 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 DOM Query Engine 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 DOM Query Engine MCP in Mastra AI

Install the package using `npm install @mastra/mcp@latest` to get the necessary client. Instantiate a new `MCPClient` with the server URL, then fetch the tools and pass them directly to your Mastra AI Agent instance.

Yes, because Mastra AI features a native workflow engine with exponential backoff. If the `query_dom` tool fails due to a network timeout or malformed HTML stream, the workflow automatically retries the operation based on your backoff settings.

Absolutely. You can run the `query_dom` tool to check for specific elements, then use the returned text to branch your Mastra AI workflow. This allows you to handle different page layouts dynamically.

The MCP Server supports both SSE and Streamable HTTP transports. Mastra AI auto-detects the transport type when you register the server URL. This ensures a hassle-free setup without manual socket configuration.

The server processes raw HTML payloads and CSS queries in isolated, single-use environments managed by the Vinkius MCP platform. Vinkius handles the underlying infrastructure, ensuring that your extracted data is never exposed to external networks or written to persistent storage. Your scraped content remains entirely private.

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