How do I connect Browserbear to my AI client?

You subscribe to the MCP on Vinkius and enter your Browserbear API Key. Once connected, you can use it immediately in any MCP-compatible client like Claude or Cursor.

Can I change the URL when running a task?

Yes. You can use the run_task capability to trigger an automation with dynamic overrides, such as a different starting URL or specific form data.

What kind of web data can I get?

You can retrieve structured scraped data and direct URLs for screenshots through the capabilities provided by the MCP.

Do I need to use the Browserbear dashboard?

No. While you can use the dashboard, this MCP allows you to manage tasks, runs, and projects directly through your AI agent.

Can I take screenshots of any website?

Yes, the take_screenshot capability allows you to capture a visual of any URL with specific dimensions and wait times.

Can I trigger a browser task with a different starting URL?

Yes! Use the run_task capability and provide the Task ID. In the overrides field, you can pass a JSON object like {"url": "https://newsite.com"} to change the starting point dynamically.

How do I see the screenshot captured by a task?

Simply ask the agent to get_run and provide the Run ID. Once the status is 'finished', the response will include a screenshot_url that you can click to view the image.

Does the integration allow taking a quick screenshot without a saved task?

Yes. Use the take_screenshot action and provide the URL. It will create a simplified run that captures the page and returns the result URL once processed.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Browserbear 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. Run web scrapers and take screenshots through your AI agent.

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 Browserbear.

01
Take screenshot
This capability captures a screenshot of a specific URL.
02
Get run
Use this to check the current status and final results of a specific run.
03
Create task
This capability lets you set up a brand new browser automation task.
04
Delete run
This capability removes a specific task run record from your history.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Browserbear.

05
Get account usage
Use this to check your current account usage statistics.
06
Get task
This capability retrieves the specific configuration and details of a saved task.
07
List projects
This capability returns a list of all projects within your account.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Browserbear.

08
List runs
Use this to see a list of all previous task runs.
09
List tasks
This capability provides a list of all your saved browser automation tasks.
10
Run task
This capability triggers a new execution of a specific task, allowing for dynamic overrides.

Real work

What teams actually run

Automated Web Scraping

Your agent can pull structured data from websites by running pre-configured scraping tasks.

Visual Regression Testing

You can trigger screenshots of specific URLs to check for UI changes.

Competitor Monitoring

Set up tasks to periodically check competitor sites and report findings to your agent.

Form Automation

Use the agent to fill out web forms as part of a larger automated workflow.

Automate a task

Put Browserbear 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

Browserbear 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 Browserbear 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

855ms average. Fast in production.

Browserbear is checked daily against the live service.

Daily averagePeak 964ms

Oct 3Today

Fastest day: 707ms
Slowest day: 964ms
14-day trend: Slowing+7%

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 Browserbear, so you can see the experience inside your AI.

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

Browserbear Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_kg9BYjzuqJpLSOraZxY02DI1X9KRTKbBI7gJO8S8/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 — Browserbear capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "browserbear-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_kg9BYjzuqJpLSOraZxY02DI1X9KRTKbBI7gJO8S8/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 Browserbear in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Browserbear owners hand off.

This MCP is for professionals who need to automate repetitive web interactions without writing custom browser code.

01
QA Engineers
They hand off visual regression testing and result inspection to the agent.
02
Growth Marketers
They use the agent to automate lead gathering and competitor monitoring.
03
Developers
They integrate browser interactions into their coding workflows using natural language.

FAQ

Questions Browserbear owners ask.

01
How do I connect Browserbear to my AI client?
You subscribe to the MCP on Vinkius and enter your Browserbear API Key. Once connected, you can use it immediately in any MCP-compatible client like Claude or Cursor.
02
Can I change the URL when running a task?
Yes. You can use the run_task capability to trigger an automation with dynamic overrides, such as a different starting URL or specific form data.
03
What kind of web data can I get?
You can retrieve structured scraped data and direct URLs for screenshots through the capabilities provided by the MCP.
04
Do I need to use the Browserbear dashboard?
No. While you can use the dashboard, this MCP allows you to manage tasks, runs, and projects directly through your AI agent.
05
Can I take screenshots of any website?
Yes, the take_screenshot capability allows you to capture a visual of any URL with specific dimensions and wait times.
06
Can I trigger a browser task with a different starting URL?
Yes! Use the run_task capability and provide the Task ID. In the overrides field, you can pass a JSON object like {"url": "https://newsite.com"} to change the starting point dynamically.
07
How do I see the screenshot captured by a task?
Simply ask the agent to get_run and provide the Run ID. Once the status is 'finished', the response will include a screenshot_url that you can click to view the image.
08
Does the integration allow taking a quick screenshot without a saved task?
Yes. Use the take_screenshot action and provide the URL. It will create a simplified run that captures the page and returns the result URL once processed.

Explore

More in Productivity

Connect Browserbear 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

Take screenshot

Get run

Create task

Delete run

05-07

Get account usage

Get task

List projects

08-10

List runs

List tasks

Run task

What teams actually run

Automated Web Scraping

Visual Regression Testing

Competitor Monitoring

Form Automation

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

Browserbear Connector

Claude Desktop

QA Engineers

Growth Marketers

Developers

How do I connect Browserbear to my AI client?

Can I change the URL when running a task?

What kind of web data can I get?

Do I need to use the Browserbear dashboard?

Can I take screenshots of any website?

Can I trigger a browser task with a different starting URL?

How do I see the screenshot captured by a task?

Does the integration allow taking a quick screenshot without a saved task?

ScreenshotOne AI Connector

Browse AI AI Connector

ScreenshotAPI AI Connector

Cloud BOT AI Connector

Suggestions

Web Scraper AI Connector

GitScrum Tasks AI Connector

Webflow AI Connector

Webflow AI Connector