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

Q: How do I initialize the HTML DOM Query Engine in Pydantic AI?

Install pydantic-ai-slimmcp. Use MCPToolset with your Vinkius endpoint, and include it in the toolsets array when creating your agent.

Q: What input does this MCP server require?

The querydom tool requires two arguments: the raw HTML string and the CSS selector. It processes the string directly.

Enforce strict runtime validation on DOM extractions by connecting the HTML DOM Query Engine to Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect HTML DOM Query Engine to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe HTML extraction

Scraping the web is notoriously fragile. Target sites change their markup, and suddenly your agent is hallucinating data. The `query_dom` tool gives your agent a deterministic way to extract text and attributes using CSS selectors. When you pair this with Pydantic AI, you get runtime validation. The agent pulls the data, and the framework strictly validates the output against your Pydantic models. If the target site changes its CSS classes, the agent fails loudly instead of corrupting your database.

Wire up the MCP Server

Getting this running requires the unified toolset approach. You install the slim package with MCP support, then initialize MCPToolset with your Vinkius HTTP endpoint. Pass that toolset directly to your Agent constructor. Do not use the deprecated HTTP server classes. The framework handles the transport layer, exposing the querying capabilities instantly.

Build model-agnostic pipelines

You might want to use a fast local model for simple extraction and switch to Claude for complex reasoning. Because Pydantic AI is model-agnostic, your DOM querying logic stays exactly the same regardless of the underlying LLM. The agent takes the raw HTML string, executes the CSS query, and returns the exact node text. You get the same predictable JSON output whether you are running a massive frontier model or a tiny open-source alternative.

Setup guide

Set up HTML DOM Query Engine MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "html-dom-query-engine-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to HTML DOM Query Engine tools.",
)

result = await agent.run("List recent HTML DOM Query Engine transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp]. Use MCPToolset with your Vinkius endpoint, and include it in the toolsets array when creating your agent.

Yes. The engine uses deterministic CSS selectors to extract text. Pydantic AI then validates that exact output against your schema, ensuring zero silent failures.

The `query_dom` tool requires two arguments: the raw HTML string and the CSS selector. It processes the string directly.

Yes. Since Pydantic AI is model-agnostic, any compatible local model can invoke the querying tools to extract DOM elements.

The server runs in a zero-trust environment. Your raw HTML strings and extracted attributes are processed in isolated memory. Once the response ships back to your client, the sandbox is completely wiped.

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