How to Use the Browse AI MCP in Windsurf

Q: How do I connect my Browse AI account to Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the remote server configuration under the mcpServers key. Once you hit save and refresh the MCP panel, Cascade instantly discovers all ten extraction tools.

Q: Can Windsurf run multiple Browse AI robots at the same time?

Yes, Cascade can initiate parallel runs by calling runrobot multiple times in a single session. It manages the queue by checking getsystemstatus and tracks each individual task ID autonomously.

Q: How does Windsurf handle errors during Browse AI execution?

If a run fails, Cascade uses gettask to inspect the error logs returned by the platform. It then adjusts the input parameters or checks getrobot to see if the scraper configuration needs to be modified.

Let Windsurf run your data extraction robots and pull scraped web data directly into your active workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to Windsurf

Create your Vinkius account to connect Browse AI to Windsurf 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 Browse AI with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Scraping Chains in Windsurf

This Browse AI MCP Server lets Windsurf trigger scraping tasks and monitor progress without you having to manually prompt individual steps. When Cascade needs external data, it calls `run_robot` to start the extraction and automatically tracks the job status using `get_task`. You specify the target site, and Cascade handles the queue management. It checks `get_system_status` to ensure the platform is ready, then processes the output the moment the robot finishes its run.

Bulk Data Extraction and Workspace Import

Cascade uses `list_bulk_runs` to identify large-scale data extractions and imports the results straight into your code files. Instead of downloading CSVs manually, your editor pulls the payload with `get_bulk_run` and formats it into your local JSON or database files. The agent handles the entire pipeline from finding the right run to parsing the nested data. It uses the active context of your project to map the incoming fields directly to your frontend components or database schemas.

Continuous Monitoring Setup via Cascade

Set up schedule tracking on target sites directly through your editor using `create_monitor`. Cascade reads your local configuration files, checks your active scraper list with `list_robots`, and configures automated intervals for your extraction tasks. The agent verifies the setup by calling `list_monitors` to confirm the schedule is active. This MCP integration lets you inspect the configuration of the specific robot with `get_robot` to troubleshoot the parameters.

Setup guide

Set up Browse AI MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Browse AI MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Browse AI payment history." If connected, Cascade will call the Browse AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "browse-ai-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 Browse AI. 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 Browse AI 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 Browse AI MCP in Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the remote server configuration under the `mcpServers` key. Once you hit save and refresh the MCP panel, Cascade instantly discovers all ten extraction tools.

Yes, Cascade can initiate parallel runs by calling `run_robot` multiple times in a single session. It manages the queue by checking `get_system_status` and tracks each individual task ID autonomously.

If a run fails, Cascade uses `get_task` to inspect the error logs returned by the platform. It then adjusts the input parameters or checks `get_robot` to see if the scraper configuration needs to be modified.

Yes, you can ask Cascade to list your active trackers. It uses `list_monitors` to fetch the active schedule for any specific robot ID and displays the frequency settings directly in your chat panel.

Vinkius runs this MCP Server in an isolated, single-tenant V8 sandbox that destroys itself after your session ends. Your scraper configurations, monitor schedules, and extracted web payloads are never stored on our servers or used for model training.

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