Browserless Connector for AI agents.
8 live capabilities
Automate web scraping and PDF generation from any live URL.
Waiting for input…
Why people use Browserless
Browserless : Automating Web Scraping and PDF Generation
With this Connector, your AI agent does the clicking and waiting for you. You just give it a URL and tell it what to grab. It handles the headless browser logic in the cloud and hands you the final data or a PDF file. You get the results without ever opening a window.
What Vinkius changes
You get a cloud-based browser that your AI agent can control to perform any web-based task.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Visual Regression Testing
A QA engineer asks the agent to take a screenshot of the login page to check if a new CSS update broke the layout.
- Real-world use case 02
Bulk PDF Conversion
A content manager asks the agent to convert a list of 10 news URLs into a set of PDF documents for a weekly newsletter.
- Real-world use case 03
Debugging Rendered Content
A web developer needs to see why a specific element isn't appearing and asks the agent to pull the fully rendered HTML.
Complete set · 8capabilities
The complete Browserless capability set.
These are the exact actions your AI can choose when you ask it to work with Browserless.
01—04
4 capabilities in this set.
Part of 8 available through Browserless.
- 01 Capability
Check system health
See if the Browserless service is up and running. This helps you confirm your connection is active before starting a big task.
- 02 Capability
Generate pdf
Turn a live URL into a formatted PDF document. It's great for saving web articles or reports for offline reading.
- 03 Capability
Get account config
Look up your current account settings and limits. Use this to make sure your permissions are set correctly.
- 04 Capability
Get page content
Pull the fully rendered HTML from a website. This is perfect for sites that rely heavily on JavaScript to show content.
05—08
4 capabilities in this set.
Part of 8 available through Browserless.
- 05 Capability
Get usage stats
See how much of your quota you've used. It helps you keep track of your costs and activity levels.
- 06 Capability
List active sessions
See every browser window currently running in your account. Use this to manage your active tasks and close old ones.
- 07 Capability
Run scrape
Execute a custom script to pull specific data from a page. You can provide selectors to get exactly what you want.
- 08 Capability
Take screenshot
Capture a visual image of a URL using a headless browser. You can take standard or full-page captures for your docs.
Set up in minutes
One URL. Then ask Browserless to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Browserless 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_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Browserless for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless URL.
- Step 03
Save and start
Save the connection and enable Browserless in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"browserless": {
"url": "https://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless
Open Agent mode in chat and ask: "Using Browserless, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"browserless": {
"url": "https://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless
Ask Copilot: "Using Browserless, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"browserless": {
"url": "https://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless
Open Cascade and ask: "Using Browserless, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"browserless": {
"url": "https://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless
Ask Cline: "Using Browserless, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add browserless --transport http "https://edge.vinkius.com/vk_preview_h3Nme4Dkj4tFYSxYJdJHzAY5a6RVLil3lKFSLlJx/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 Browserless
Ask Claude: "Using Browserless, show me...". 8 tools are ready
Where the request belongs
Work Browserless can move forward.
This is for the QA engineer who needs consistent visual checks, the content manager tired of manual PDF exports, and the developer debugging complex frontend renders.
QA Engineer
Automates visual regression testing by capturing screenshots of UI changes on a Tuesday afternoon.
Content Manager
Converts web articles into PDFs for distribution without manually saving every page.
Web Developer
Debugs rendered HTML content on JavaScript-heavy sites to see what the user actually sees.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsBrowserbear
Automate browser tasks via Browserbear. take screenshots, scrape data, and run multi-step automations directly from any AI agent.
Browserbase
Cloud browser infrastructure for AI agents. create, control, and manage headless Chromium sessions via CDP for automated web interaction.
Browserless (Playwright Cloud)
Equip your AI with a remote headless browser to scrape, interact, and run Playwright safely via cloud.
Hyperbrowser (Web Infra for AI)
Cloud browsers for AI agents via Hyperbrowser. manage sessions, scrape pages, and extract structured data.
Urlbox
Render websites as high-quality screenshots and PDFs with a cloud API that handles responsive layouts and dynamic content.
PagePixels
Capture website screenshots and generate visual previews programmatically with an API that handles rendering at any resolution.
Bring your own AI
Change the model, client or framework. Keep Browserless 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 Browserless.
The practical details behind the request, access and result.
Can the Browserless MCP take screenshots of entire webpages?
Yes, it can capture full-page screenshots of any URL. This is perfect for creating documentation or checking how a site looks on different screen sizes.
How do I use Browserless MCP to get data from a website?
You can ask your AI agent to scrape specific parts of a page. It uses a headless browser to load the site and pull out the information you need, even if the site uses complex scripts.
Can Browserless MCP create PDF files from URLs?
Yes, it can convert any live web page into a polished PDF document. You just provide the link, and the agent handles the conversion for you.
Is Browserless MCP good for scraping JavaScript websites?
It's ideal for that. Because it runs a real headless Chrome instance, it can render the full content of pages that standard scrapers usually miss.
How do I check my usage with Browserless MCP?
You can ask your agent to check your account stats. It will pull your current usage data and configuration directly from your account to keep you informed.
Can I use Browserless MCP for visual testing?
Absolutely. It's frequently used by QA teams to automate visual regression by taking consistent screenshots of web components or full pages.
Can I take a full-page screenshot using the agent?
Yes! Use the take_screenshot capability and in the options field, provide a JSON string like {"fullPage": true}. Browserless will capture the entire length of the page.
How do I convert a web page to a PDF?
Simply ask the agent to generate_pdf and provide the URL. It will use Browserless to render the page and return the generated PDF file (usually as a binary response or link).
Does the integration allow scraping specific data fields?
Yes. Use the run_scrape action and provide the URL along with an elements array containing the selectors and names for the data you want to extract.
One connection away
Give your agent a direct line to Browserless.
Connect Browserless once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available