Cheerio DOM Connector for AI agents.
1 live capability
Extract specific data from massive web pages without hitting token limits.
Waiting for input…
Why people use Cheerio DOM
HTML DOM Query Engine for Precision Web Scraping
This Connector lets your agent act like a scalpel. You just tell it which part of the page to look at, and it returns the exact value. It cuts out the noise so you can get straight to the data.
What Vinkius changes
Your agent gets the exact data it needs without wasting a single token on irrelevant HTML.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
E-commerce Price Tracking
An agent scrapes a product page, pulls the price using a CSS selector, and logs it to a sheet without reading the whole site code.
- Real-world use case 02
Gallery Scraping
You need all image links from a site; the agent uses a selector to grab every source attribute instantly.
- Real-world use case 03
Documentation Parsing
Extracting specific code blocks from a huge documentation page without reading the whole site.
Complete set · 1capability
The complete Cheerio DOM capability set.
These are the exact actions your AI can choose when you ask it to work with Cheerio DOM.
01
1 capability in this set.
Part of 1 available through Cheerio DOM.
- 01 Capability
Query dom
Pass a raw HTML string and a CSS selector to get specific text or attributes. It handles the parsing so your agent stays focused on the data.
Set up in minutes
One URL. Then ask Cheerio DOM to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Cheerio DOM from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Cheerio DOM, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Cheerio DOM for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Cheerio DOM URL.
- Step 03
Save and start
Save the connection and enable Cheerio DOM in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"html-dom-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Cheerio DOM
Open Agent mode in chat and ask: "Using Cheerio DOM, help me...". 1 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"html-dom-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Cheerio DOM
Ask Copilot: "Using Cheerio DOM, help me...". 1 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"html-dom-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Cheerio DOM
Open Cascade and ask: "Using Cheerio DOM, help me...". 1 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"html-dom-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Cheerio DOM
Ask Cline: "Using Cheerio DOM, help me...". 1 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add html-dom-query-engine --transport http "https://edge.vinkius.com/vk_preview_yforvmpWi3y9TqnYhrCHzOXtUdI6qMtPsOkV6gLr/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Cheerio DOM
Ask Claude: "Using Cheerio DOM, show me...". 1 tools are ready
Where the request belongs
Work Cheerio DOM can move forward.
Data engineers tired of messy scraping results, web automation hobbyists, and developers building agents that need to interact with complex websites without hitting token ceilings.
Web Scraper
Pulls specific product prices from massive e-commerce pages without crashing the agent.
Automation Engineer
Extracts links from complex navigation menus to build automated workflows.
Data Analyst
Grabs specific table data from old-school web portals into clean lists.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
HTML DOM Path Generator
Generate robust, deterministic CSS selectors from HTML snippets to prevent brittle web scraping.
HTML to Text Extractor
Stop wasting AI context on messy HTML code. Instantly strip CSS, tags, and scripts to extract perfectly readable Plain Text.
ZenRows
Scrape HTML, bypass anti-bots, and extract structured data using ZenRows' advanced proxy and browser network.
Olostep
Scrape web pages at scale with a headless browser API that renders JavaScript and returns clean structured data instantly.
Octoparse
Scrape data from any website visually with a no-code web scraper that handles pagination, login, and JavaScript rendering.
WebScrapingAPI
Scrape HTML, render JavaScript, and retrieve structured SERP data using WebScrapingAPI's high-proxy network.
Bring your own AI
Change the model, client or framework. Keep Cheerio DOM connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Cheerio DOM.
The practical details behind the request, access and result.
How does HTML DOM Query Engine help with web scraping?
It lets your agent grab specific data points like prices or links from huge pages without having to read the whole file. This keeps your agent focused and prevents it from getting overwhelmed by unnecessary code.
Can it handle very large HTML files?
Yes, it handles massive HTML payloads by parsing them in the background. This means you can process pages with thousands of lines of code without hitting token limits or crashing your agent.
Does it work with complex CSS selectors?
It works with any standard CSS selector. You can use IDs, classes, and nested selectors to pinpoint exactly which piece of information you need to extract.
How does this save on AI costs?
It saves money by significantly reducing the amount of text sent to the AI. Since you only send the final extracted data instead of a whole webpage, you use fewer tokens for every request.
Can I extract attributes like image sources?
Yes, it can pull specific attributes like src or href from any element. This is useful for gathering image galleries or mapping out links on a website.
Does it download the URL?
No, it parses raw HTML strings that you pass to it.
Can it extract link URLs?
Yes, just pass 'href' in the attribute parameter.
Is it fast?
Yes, it uses Cheerio, which runs entirely in memory without a headless browser.
One connection away
Give your agent a direct line to Cheerio DOM.
Connect Cheerio DOM once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available