How to Use the Firecrawl MCP in Windsurf

Q: How does Windsurf use Firecrawl to scrape dynamic JavaScript sites?

Cascade handles this by calling scrapeurl, which executes client-side JavaScript on Firecrawl's hosted browsers before returning the clean markdown. You do not need to configure headless browsers or handle proxies yourself.

Q: How do I monitor my credit limits with the Firecrawl MCP Server on Windsurf?

Cascade can check your balance automatically. It runs getapiusage behind the scenes to show you exactly how many credits you have left before you trigger a massive domain crawl.

Q: Does Cascade handle multi-page sites automatically?

Yes, Cascade chains the tools. It first runs mapwebsitestructure to find the pages, then initiates startcrawl to pull the content, and finally checks getcrawlstatus until the raw text is ready.

Turn entire websites into clean markdown inside Windsurf with Cascade's autonomous multi-step Firecrawl scraping.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to Windsurf

Create your Vinkius account to connect Firecrawl 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 Firecrawl with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map site structures with Cascade

The `map_website_structure` tool finds every single URL on a target domain without wasting your Firecrawl API budget on blind scraping. Cascade takes this map and automatically plans which pages to scrape inside your Windsurf workspace, skipping the manual configuration step entirely. You do not have to write custom crawl rules. Cascade analyzes the site layout, identifies the relevant pages, and queues up the extraction process.

Deep site crawling via Windsurf MCP Server

The `start_crawl` tool kicks off an asynchronous deep crawl across a whole domain to convert raw HTML into clean markdown. Cascade monitors this background job by calling `get_crawl_status` periodically, letting you focus on writing code while the data populates. If a crawl goes off the rails or runs too long, Cascade calls `cancel_active_crawl` to protect your credits. You get raw, LLM-ready markdown delivered straight to your active workspace without managing network requests.

On-demand URL scraping and cost tracking

The `scrape_url` tool converts a single web page into clean, structured markdown instantly. Cascade uses this MCP Server capability for real-time reference, pulling down documentation pages or API specs exactly when you ask a question. To keep your billing in check, Cascade runs `get_api_usage` to verify your remaining credits before initiating large scrapes. This keeps your external data pulls transparent and prevents unexpected API blocks.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "firecrawl-extended-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 Firecrawl. 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 Firecrawl 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 Firecrawl MCP in Windsurf

Cascade handles this by calling `scrape_url`, which executes client-side JavaScript on Firecrawl's hosted browsers before returning the clean markdown. You do not need to configure headless browsers or handle proxies yourself.

Yes, Cascade watches your active scraping jobs. If a crawl is taking too long, Cascade calls `cancel_active_crawl` to stop the job instantly and prevent credit waste.

Cascade can check your balance automatically. It runs `get_api_usage` behind the scenes to show you exactly how many credits you have left before you trigger a massive domain crawl.

Yes, Cascade chains the tools. It first runs `map_website_structure` to find the pages, then initiates `start_crawl` to pull the content, and finally checks `get_crawl_status` until the raw text is ready.

Your crawled markdown and site URLs are processed through Vinkius's secure sandboxed MCP Server environment. No raw HTML or scraped credential data is ever stored on our servers, keeping your target data isolated.

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