Browse AI Connector for AI agents.
10 live capabilities
Automate web scraping and data extraction from any website.
Waiting for input…
Why people use Browse AI
Browse AI for Solving Manual Web Data Entry
With this Connector, you just tell your agent to run a robot. It handles the navigation, waits for the page to load, and grabs the data. You get a clean JSON file ready for analysis in seconds.
What Vinkius changes
You turn your AI agent into a direct pipeline for live web intelligence.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Competitor Price Tracking
A marketing manager asks their agent to run a robot on a competitor's pricing page and get the current costs for 10 different products.
- Real-world use case 02
Bulk Product Research
A researcher needs to pull 500 product descriptions from a retail site and have the agent summarize the common themes.
- Real-world use case 03
Automated News Gathering
A journalist uses a monitor to detect changes on a government website and asks the agent to summarize the new updates as they appear.
Complete set · 10capabilities
The complete Browse AI capability set.
These are the exact actions your AI can choose when you ask it to work with Browse AI.
01—04
4 capabilities in this set.
Part of 10 available through Browse AI.
- 01 Capability
Get task data
Pull the final JSON results from a successfully completed scraping task. This brings the actual data into your current conversation.
- 02 Capability
Get task
Check the progress of a single extraction task. It shows you if the robot is still working or if it hit an error.
- 03 Capability
List credits
See how many credits you have left and check your current plan limits. It keeps your scraping costs from becoming a surprise.
- 04 Capability
List monitors
See all your active web change monitors and their current statuses. This helps you manage your automated alerts.
05—07
3 capabilities in this set.
Part of 10 available through Browse AI.
- 05 Capability
List robots
List every extraction and monitoring robot in your Browse AI account. Use this to see your entire library of scraping workflows.
- 06 Capability
Run robot
Trigger a specific robot to scrape a target URL with custom input parameters. It's the fastest way to get data from a single page.
- 07 Capability
Run bulk task
Run a robot across multiple URLs simultaneously using Browse AI infrastructure. This is the best way to get data from a large list of pages in one go.
08—10
3 capabilities in this set.
Part of 10 available through Browse AI.
- 08 Capability
Download bulk data
Get a JSON array of all results from a finished bulk extraction run. Use this to grab everything the robot found in one move.
- 09 Capability
Get bulk task
Check the current status of a multi-URL bulk scraping task. It lets you see if your large data pull is still running or finished.
- 10 Capability
Get robot
See the full configuration and settings for a specific scraping robot. Use this to check how your robot is built and what it targets.
Set up in minutes
One URL. Then ask Browse AI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Browse AI 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_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Browse AI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI URL.
- Step 03
Save and start
Save the connection and enable Browse AI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"browse-ai-1": {
"url": "https://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI
Open Agent mode in chat and ask: "Using Browse AI, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"browse-ai-1": {
"url": "https://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI
Ask Copilot: "Using Browse AI, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"browse-ai-1": {
"url": "https://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI
Open Cascade and ask: "Using Browse AI, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"browse-ai-1": {
"url": "https://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI
Ask Cline: "Using Browse AI, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add browse-ai-1 --transport http "https://edge.vinkius.com/vk_preview_eFjufwfO5yFrM4ynCp0RQOH02U7ZRWZmMvVcNnMm/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 Browse AI
Ask Claude: "Using Browse AI, show me...". 10 tools are ready
Where the request belongs
Work Browse AI can move forward.
Data analysts who hate manual scraping, SEO managers tracking competitors, and researchers needing structured data from websites without writing custom Python scripts.
Data Analyst
Pulls bulk datasets from websites into a workspace for immediate analysis on a Tuesday afternoon.
SEO Specialist
Runs robots on competitor sites to generate market reports on the fly without leaving their chat interface.
Web Researcher
Extracts specific metrics from complex pages without visiting the dashboards manually.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsBrowse AI
Extract data from any website without code using trained robots that monitor pages and deliver structured results automatically.
Grepsr
Automate web scraping via Grepsr. manage reports, trigger crawls, and retrieve data directly via AI.
Nimbleway
Web data collection and scraping via Nimbleway. extract content and search the web directly from your AI agent.
Diffbot
Automate web data extraction via Diffbot. turn any website into structured JSON data for articles, products, discussions, and more directly from any AI agent.
Apify
Run web scraping actors, collect structured data, and manage storage datasets for large-scale data extraction projects.
Olostep
Scrape web pages at scale with a headless browser API that renders JavaScript and returns clean structured data instantly.
Bring your own AI
Change the model, client or framework. Keep Browse AI 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 Browse AI.
The practical details behind the request, access and result.
Can Browse AI MCP scrape websites that don't have an API?
Yes, it uses robots to scrape any site. It handles the heavy lifting of navigating the page and extracting the data you need into a structured format.
How does Browse AI MCP handle multiple URLs at once?
It uses a bulk task feature. You can give your agent a list of URLs, and it will run the extraction across all of them concurrently.
Can I see the JSON data directly in my chat?
Yes. Once the agent finishes the scraping task, it can pull the final JSON results and present them to you directly in the conversation.
Does Browse AI MCP work with Cursor and Claude?
Yes, it works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
How do I check my scraping credits with Browse AI MCP?
Your agent can check your quota and plan limits for you instantly, so you can keep track of your usage without logging into a dashboard.
Can my AI start a data extraction and let me know when it finishes?
Yes! You can ask your agent to run_robot on a certain URL. The agent receives the newly created task ID and can immediately invoke get_task sequentially to poll for completion. Once successful, it calls get_task_data to dump the JSON right into your conversation without breaking workflow.
How do bulk operations work natively through the agent?
When you have a trained robot, you can feed the run_bulk_task command an array of different URLs. Browse AI's backend splits them virtually into independent task instances. Your agent tracks the bulk run via get_bulk_task and eventually pulls the mega JSON merge using download_bulk_data.
Is there a risk of my agent suddenly spending all my API credits?
You have complete visibility—the agent can query list_credits at any moment to inform you precisely of your available balance and monthly limit. Also, since capabilities execute your natural directives, your AI agent only triggers extractions you specifically prompt for.
One connection away
Give your agent a direct line to Browse AI.
Connect Browse AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available