Zyte Connector for AI agents.
3 live capabilities
Pull structured web data and search results from any site.
Waiting for input…
Why people use Zyte
Zyte for Bypassing Anti-Bot Measures and Web Scraping
With this Connector, you just tell your agent to grab the latest headlines from a news site or navigate through a multi-step login. The Connector handles the clicks, the proxy rotation, and the browser rendering. You get a clean table of data in seconds.
What Vinkius changes
You get clean, structured data from any site without managing the underlying scraping infrastructure.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Competitive Intelligence
Ask your agent to check what your competitors are ranking for in the UK and give you the top 5 organic links.
- Real-world use case 02
Dataset Building
Tell your agent to go to a retail site, click 'Next' until the end, and grab every product name into a list.
- Real-world use case 03
Content Monitoring
Have your agent take a screenshot of a homepage to verify if a new banner or promotion is live.
Complete set · 3capabilities
The complete Zyte capability set.
These are the exact actions your AI can choose when you ask it to work with Zyte.
01—03
3 capabilities in this set.
Part of 3 available through Zyte.
- 01 Capability
Get stats
Retrieve your current API usage and success rates. Use this to keep an eye on your costs and consumption limits.
- 02 Capability
Extract data
Pull web data from any target URL while handling browser rendering and anti-bot measures for you.
- 03 Capability
Search data
Fetch organic search results from Google and other search domains for market research and SEO analysis.
Set up in minutes
One URL. Then ask Zyte to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Zyte 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_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Zyte for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte URL.
- Step 03
Save and start
Save the connection and enable Zyte in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"zyte": {
"url": "https://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte
Open Agent mode in chat and ask: "Using Zyte, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"zyte": {
"url": "https://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte
Ask Copilot: "Using Zyte, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"zyte": {
"url": "https://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte
Open Cascade and ask: "Using Zyte, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"zyte": {
"url": "https://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte
Ask Cline: "Using Zyte, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add zyte --transport http "https://edge.vinkius.com/vk_preview_ItnEhBQ9VfWSoTm1kEsGQnKXjmpuAs456LmANU3G/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 Zyte
Ask Claude: "Using Zyte, show me...". 3 tools are ready
Where the request belongs
Work Zyte can move forward.
This is for the data scientist tired of cleaning messy HTML, the SEO specialist monitoring global rankings, and the developer who needs to debug a scraper without building a full backend.
Data Scientist
Gathering large datasets from websites that have aggressive anti-bot protections without managing proxy pools.
SEO Specialist
Monitoring organic search results and localized content across different countries to track global rankings.
Web Developer
Inspecting browser-rendered content and testing web scraping logic directly from a code editor.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsBright Data
Access the world's #1 web data platform. bypass anti-bot protections, extract structured search engine data, and manage scraping browsers directly from your AI agent.
Nimbleway
Web data collection and scraping via Nimbleway. extract content and search the web directly from your AI agent.
Olostep
Scrape web pages at scale with a headless browser API that renders JavaScript and returns clean structured data instantly.
ScraperAPI
Equip your AI agent with proxy rotation and headless browsers to extract HTML, Google SERPs, and Amazon data at scale.
ZenRows
Scrape HTML, bypass anti-bots, and extract structured data using ZenRows' advanced proxy and browser network.
Oxylabs
Scrape any website via Oxylabs. extract Google SERPs, Amazon products, Bing and Yandex results, or any arbitrary URL with JS rendering from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Zyte 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 Zyte.
The practical details behind the request, access and result.
Can the Zyte MCP bypass CAPTCHAs?
Yes, this Connector handles anti-bot measures and proxy rotation automatically so your agent can get the data it needs without being blocked by common security hurdles.
Does the Zyte MCP work on sites that require JavaScript?
It does. The Connector uses browser rendering to ensure that the content your AI agent sees is the same as what a human sees in a real browser.
Can I use the Zyte MCP to see search results from different countries?
Yes, you can route your requests through specific countries to see localized search results and content from different geographic regions.
How does the Zyte MCP handle browser actions like clicking?
It performs complex sequences of actions like clicking buttons, scrolling through pages, and waiting for specific elements to load before extracting data.
Is the Zyte MCP good for large-scale data mining?
It's ideal for data mining because it manages the difficult infrastructure like proxy rotation and headless browser management for you.
Can I see my API usage through the Zyte MCP?
Yes, you can ask your agent to show your current usage, costs, and success rates directly in the chat by using the stats capability.
Can I take a screenshot of a website using this server?
Yes! Use the extract_data capability and set the screenshot parameter to true. The agent will return the visual state of the page as requested.
How do I get organic search results from Google?
Use the search_data capability, specifying 'google.com' as the domain and your keywords as the query. You can also set maxResults to control the list length.
Is it possible to monitor my Zyte API spending?
Yes, by using the get_stats capability. Note that this requires you to provide your ZYTE_DASHBOARD_API_KEY during setup.
One connection away
Give your agent a direct line to Zyte.
Connect Zyte once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available