How to Use the HTML DOM Query Engine MCP in OpenAI Agents SDK

Q: What happens if the CSS selector matches nothing?

The querydom tool returns an empty result. Your OpenAI agent sees the empty response and can decide whether to try a different selector or flag the page as changed.

Extract exact text and attributes from massive HTML payloads directly inside your OpenAI Agents SDK production workflows.

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 OpenAI Agents SDK

Create your Vinkius account to connect HTML DOM Query Engine to OpenAI Agents 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 DOM Query Engine with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse raw HTML payloads instantly

Your production agent needs to pull specific prices or metadata out of raw HTML. You don't want to rely on the LLM guessing the structure of a five-megabyte document. The `query_dom` tool takes the raw string and a CSS selector, pulling exactly what you ask for. This setup bypasses the token limits and hallucination risks of feeding raw markup to your model. You pass the HTML and a selector like ".price". The engine returns deterministic JSON containing just the matched nodes.

Auto-discover this MCP Server

OpenAI Agents SDK makes connecting this MCP server trivial. You initialize MCPServerStreamableHttp with your Vinkius endpoint and pass it directly to the agent constructor. Set cacheToolsList=True to cut down on startup latency. Once connected, the agent's built-in guardrails validate the inputs before triggering the parser. If the agent tries to send malformed CSS selectors, the framework catches it. You get full visibility into every extraction step right in the OpenAI tracing dashboard.

Feed specialized web agents

Complex workflows usually require specialized agents passing data back and forth. You can assign the HTML DOM Query Engine to a dedicated scraper agent. That agent pulls the raw markup, extracts the target text, and hands the clean data off to a summarization agent. This keeps your architecture modular. The scraper agent handles the messy DOM parsing using standard CSS selectors. The downstream agents only ever see clean, validated text nodes, keeping your OpenAI token costs predictable.

Setup guide

Set up HTML DOM Query Engine MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all HTML DOM Query Engine tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives HTML DOM Query Engine tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HTML DOM Query Engine tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="HTML DOM Query Engine Agent",
            instructions="You have access to HTML DOM Query Engine tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the openai-agents package. Use MCPServerStreamableHttp with your Vinkius endpoint url. Pass it in the mcp_servers array when you build your agent.

Yes. The engine processes the HTML string directly without spinning up a headless browser. Your agent just passes the string and the CSS selector.

The `query_dom` tool returns an empty result. Your OpenAI agent sees the empty response and can decide whether to try a different selector or flag the page as changed.

Regular expressions break on malformed HTML. This MCP server parses the actual DOM tree structure, so it handles nested tags and messy markup correctly.

The engine processes your raw HTML strings and CSS selectors in a zero-trust V8 Isolate Sandbox. The data exists only for the duration of the query execution. Once the extraction finishes, the ephemeral environment is destroyed.

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