HTML DOM Query Engine

HTML DOM Query Engine MCP Connector for Claude

F

Extract specific text and attributes from massive HTML payloads instantly using CSS selectors. Fast, memory-efficient DOM parsing.

1 tools Official Updated Jun 28, 2026 Official Vinkius Partner

If an AI agent needs to scrape a product price from a 20,000-line e-commerce HTML page, passing the entire raw HTML to the LLM destroys its token limit and leads to hallucination. This MCP allows the LLM to pass the raw string and a CSS selector, instantly returning just the target data.

The Superpowers

  • Token Saver: Offloads heavy DOM parsing to the native V8 runtime via Cheerio.
  • Precision Scraping: Supports complex CSS selectors (e.g. #main .price) and extracts specific attributes like href or src.
html-parsingcss-selectorsdata-extractionweb-automationdom-manipulation

1 tools expose this connector's capabilities to your AI agent.

query_dom

Pass the HTML string and a CSS query (e.g. "h1", ".price", "#title"). Returns the matched text content or attributes. Parses a raw HTML string and extracts text or attributes using a CSS selector deterministically

See how to talk to your AI agent using HTML DOM Query Engine.

Extract the text from `.product-price` from this 5,000 line HTML file.

✅ **Matches Found:** 1. `$149.99`

Extract all image source URLs (`src`) from the `.gallery img` selector.

✅ **Matches:** Extracted 12 `src` attributes successfully.

Get the text inside the `<h1>` tag.

✅ **Matched Text:** 'Welcome to our API documentation.'

No, it parses raw HTML strings that you pass to it.

Related Connectors