How to Use the Browserbear MCP in Cursor

Q: How do I configure Browserbear inside my Cursor editor?

Add the server configuration to your .cursor/mcp.json file at the project root or globally in your home directory. Once saved, Cursor loads the tools automatically, allowing your agent to call them in chat or Composer mode.

Q: Can Cursor trigger a Browserbear task during a debugging session?

Yes, the agent can call runtask to execute a browser automation run when you are debugging. It can then pull the execution logs to verify if an external API or website is behaving as expected.

Q: How do I view my Browserbear subscription limits inside Cursor?

Ask the agent to run getaccountusage directly in the chat panel. It will return your remaining API credits and monthly run count, keeping you informed of your resource usage without leaving the code editor.

Q: Can I clean up failed execution logs from the terminal?

Yes. The deleterun tool allows you to remove unwanted execution records from your run history by passing the specific run ID.

Run browser automation and pull live scraped data directly into your Cursor codebase.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbear MCP to Cursor

Create your Vinkius account to connect Browserbear to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Browserbear with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate functional code using live scraped web data

The `get_run` tool retrieves the exact data output from a completed web automation run directly into your editor. Cursor uses this live payload to generate typed interfaces and parser logic based on real HTML structures instead of mock data. You trigger the run, wait a few seconds, and feed the raw JSON output to the agent. This MCP workflow replaces manual JSON exporting and speeds up integration testing.

Inspect your active scraper configurations inside Cursor

The `get_task` tool retrieves the exact steps and selectors of any browser automation workflow in your account. Your agent reads this structure to understand how data is extracted, allowing it to write precise backend parsers that match your scraper's output format. You can also call `list_tasks` to browse your entire library of scraping templates. This keeps your development context entirely inside the editor, eliminating the need to toggle back and forth to a browser window.

Capture UI regressions with this MCP Server

The `take_screenshot` tool generates a visual render of any URL to help you quickly catch CSS bugs or layout shifts during local development. Cursor triggers the render remotely and displays the resulting image file directly inside your chat pane. This gives you a fast feedback loop when testing public-facing staging servers. You don't need to configure local Puppeteer or Playwright instances just to check a simple layout.

Setup guide

Set up Browserbear MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Browserbear MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Browserbear transactions." If the MCP tools are loaded correctly, Cursor will call the Browserbear tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "browserbear-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Browserbear. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Browserbear now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Browserbear MCP in Cursor

Add the server configuration to your `.cursor/mcp.json` file at the project root or globally in your home directory. Once saved, Cursor loads the tools automatically, allowing your agent to call them in chat or Composer mode.

Yes, the agent can call `run_task` to execute a browser automation run when you are debugging. It can then pull the execution logs to verify if an external API or website is behaving as expected.

Ask the agent to run `get_account_usage` directly in the chat panel. It will return your remaining API credits and monthly run count, keeping you informed of your resource usage without leaving the code editor.

Yes. The `delete_run` tool allows you to remove unwanted execution records from your run history by passing the specific run ID.

All data processed by this MCP Server runs inside Vinkius's ephemeral, isolated V8 sandbox. Your API keys, scraped page data, and target URLs are transmitted securely and wiped from the execution environment immediately after the session ends.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript