How do I use Browserhub with Claude?

You connect the Browserhub MCP through Vinkius and then use your Claude client to send scraping commands via natural language.

Can I scrape a website without setting up a scraper first?

Yes, you can use the direct_scrape capability to perform one-off extractions from any URL immediately.

How do I know if my scraping job finished?

Your agent can use the get_scraping_job capability to check the status and results of any active or completed job.

Where do I manage my proxy settings?

Your agent can list available proxy locations using the list_proxy_locations capability to help manage your scraping infrastructure.

Do I need to write code to run a scraper?

No, you simply tell your AI agent to run a specific scraper or blueprint, and it handles the execution for you.

Can I scrape a URL directly without creating a scraper first?

Yes! Use the direct_scrape capability and provide the URL. It will use Browserhub's real browsers to render the page and extract data based on your parameters instantly.

How do I monitor the progress of a scraping job?

Simply ask the agent to get_scraping_job and provide the Job ID. It will return the current status (e.g., pending, running, finished) and the result data once ready.

Can I specify a proxy location for my scraping request?

Yes. When using direct_scrape, you can provide a proxy_country code. Use the list_proxy_locations capability to see the full list of supported countries in your account.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Browserhub to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn any website into structured data using natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Browserhub.

01
Get blueprint
This capability retrieves the specific configuration details for a single scraper blueprint.
02
Get scraping job
Use this to check the current status and view the final results of a specific scraping job.
03
List scraping jobs
This capability provides a full list of all your previous and current scraping jobs.
04
List proxy locations
This capability returns a list of all available proxy locations you can use for your tasks.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Browserhub.

05
Direct scrape
This capability performs a single, immediate scrape of a URL without needing a pre-configured scraper.
06
Get account balance
Use this to check how many credits you have left in your Browserhub account.
07
Get scraper
This capability fetches the configuration and details for a specific scraper.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Browserhub.

08
List blueprints
This capability shows you all the scraper blueprints currently saved in your account.
09
List scrapers
This capability returns a list of all your configured scrapers.
10
Run scraper
This capability starts a new scraping job using one of your existing scrapers.

Real work

What teams actually run

Price Monitoring

An agent can periodically run scrapers to track price changes on competitor sites.

Dataset Building

Data scientists can instruct an agent to scrape specific sites to build training sets.

Lead Generation

Researchers can trigger scrapers to pull contact information from directory websites.

Content Aggregation

Users can scrape news sites or blogs to gather information for analysis.

Automate a task

Put Browserhub to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Browserhub works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Browserhub to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

893ms average. Fast in production.

Browserhub is checked daily against the live service.

Daily averagePeak 1150ms

Oct 3Today

Fastest day: 758ms
Slowest day: 1150ms
14-day trend: Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Browserhub, so you can see the experience inside your AI.

It does not authenticate your account with Browserhub. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Browserhub Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_F9IfZPWnnyR4kONzJQmvDLDoirarcJ8VBG97e9XE/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Browserhub capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "browserhub-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_F9IfZPWnnyR4kONzJQmvDLDoirarcJ8VBG97e9XE/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Browserhub in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Browserhub owners hand off.

This MCP is built for professionals who need to pull web data into their workflows without writing custom scraping code.

01
Data Scientists
They hand off the task of gathering web datasets to their agent.
02
Market Researchers
They use the agent to monitor pricing and availability across different websites.
03
Developers
They use natural language to integrate web extraction and proxy rotation into their apps.

FAQ

Questions Browserhub owners ask.

01
How do I use Browserhub with Claude?
You connect the Browserhub MCP through Vinkius and then use your Claude client to send scraping commands via natural language.
02
Can I scrape a website without setting up a scraper first?
Yes, you can use the direct_scrape capability to perform one-off extractions from any URL immediately.
03
How do I know if my scraping job finished?
Your agent can use the get_scraping_job capability to check the status and results of any active or completed job.
04
Where do I manage my proxy settings?
Your agent can list available proxy locations using the list_proxy_locations capability to help manage your scraping infrastructure.
05
Do I need to write code to run a scraper?
No, you simply tell your AI agent to run a specific scraper or blueprint, and it handles the execution for you.
06
Can I scrape a URL directly without creating a scraper first?
Yes! Use the direct_scrape capability and provide the URL. It will use Browserhub's real browsers to render the page and extract data based on your parameters instantly.
07
How do I monitor the progress of a scraping job?
Simply ask the agent to get_scraping_job and provide the Job ID. It will return the current status (e.g., pending, running, finished) and the result data once ready.
08
Can I specify a proxy location for my scraping request?
Yes. When using direct_scrape, you can provide a proxy_country code. Use the list_proxy_locations capability to see the full list of supported countries in your account.

Explore

More in Data Management

Connect Browserhub to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get blueprint

Get scraping job

List scraping jobs

List proxy locations

05-07

Direct scrape

Get account balance

Get scraper

08-10

List blueprints

List scrapers

Run scraper

What teams actually run

Price Monitoring

Dataset Building

Lead Generation

Content Aggregation

Building your own app? The connector is yours to use.

Browserhub Connector

Claude Desktop

Data Scientists

Market Researchers

Developers

How do I use Browserhub with Claude?

Can I scrape a website without setting up a scraper first?

How do I know if my scraping job finished?

Where do I manage my proxy settings?

Do I need to write code to run a scraper?

Can I scrape a URL directly without creating a scraper first?

How do I monitor the progress of a scraping job?

Can I specify a proxy location for my scraping request?

Import.io (Web Data Extraction) AI Connector

Grepsr AI Connector

Bright Data AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Suggestions

Scrapfly AI Connector

Captain Data AI Connector

Apify AI Connector

Apify AI Connector