How to Use the Crawlbase MCP in Windsurf

Q: How does Crawlbase handle JavaScript-heavy sites inside Windsurf?

Windsurf uses scrapejsrendered to wait for client-side scripts to run before collecting the page source. Cascade reads the fully rendered DOM directly in your editor workspace.

Q: Can I chain Amazon scraping tasks autonomously with Crawlbase in Windsurf?

Yes, Cascade can autonomously call scrapeamazon to fetch product data and then run local scripts to format it. You set the end goal, and the editor handles the tool execution sequence.

Q: How do I configure Crawlbase proxy settings for Windsurf Cascade?

Open your local mcpconfig.json file and add the Crawlbase MCP server endpoint with your Vinkius token. Windsurf Cascade automatically reads the schema and exposes tools like customscrape for immediate use.

Feed real-time web data directly to Windsurf Cascade so it can crawl, bypass CAPTCHAs, and extract clean JSON on autopilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crawlbase MCP to Windsurf

Create your Vinkius account to connect Crawlbase 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 Crawlbase with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step E-Commerce Scraping in Windsurf

The `scrape_amazon` tool lets Cascade inspect deep product arrays and bypass e-commerce anti-bot blocks using this MCP server directly inside your editor. Cascade starts by targeting a specific ASIN, pulls the raw structured data, and automatically maps the pricing arrays without you writing a single crawler script. When you give Cascade a goal, it chains the Amazon tool with local file writing. It grabs the pricing arrays, writes a clean CSV to your workspace, and updates your UI frontend code in one automated pass.

Extract Dynamic JS Sites with Cascade Chain Actions

The `scrape_js_rendered` tool executes JavaScript on heavy target pages and returns the fully rendered HTML payload directly to Cascade's context window. Instead of failing on empty React divs, your editor reads the actual client-side rendered content immediately. Cascade uses this MCP server to analyze site structure on the fly. It chains `scrape_json_format` to parse key-value pairs, letting you build local mock databases from live JS-heavy endpoints with zero manual copy-pasting.

Automating Social Audits with Crawlbase MCP Server

The `scrape_linkedin` tool extracts raw profile data and business blueprint details to help Cascade run background research on target companies. Windsurf executes this tool, reads the corporate structure, and instantly maps out key decision-makers. Cascade links this tool with `scrape_twitter` and `scrape_facebook` to collect a complete social footprint for any brand. You get structured social feeds saved directly to your workspace files without writing API authentication boilerplate.

Setup guide

Set up Crawlbase 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 Crawlbase 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 Crawlbase payment history." If connected, Cascade will call the Crawlbase tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "crawlbase-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 Crawlbase. 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 Crawlbase 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 Crawlbase MCP in Windsurf

Windsurf uses `scrape_js_rendered` to wait for client-side scripts to run before collecting the page source. Cascade reads the fully rendered DOM directly in your editor workspace.

Yes, Cascade can autonomously call `scrape_amazon` to fetch product data and then run local scripts to format it. You set the end goal, and the editor handles the tool execution sequence.

Open your local `mcp_config.json` file and add the Crawlbase MCP server endpoint with your Vinkius token. Windsurf Cascade automatically reads the schema and exposes tools like `custom_scrape` for immediate use.

The Crawlbase engine automatically solves CAPTCHAs and rotates datacenter proxies in the background. Your editor receives clean HTML or JSON payloads without interrupting your development flow.

Vinkius runs the server in an ephemeral V8 sandbox, meaning your Crawlbase API tokens and raw HTML payloads never touch local storage or persistent external logs. Only the final extracted data is returned to your editor session.

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