How to Use the Firecrawl MCP in Claude

Q: How do I configure the Firecrawl MCP server on my local Claude Desktop installation?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Save the file and restart your Claude Desktop app to make the web scraping tools available in your chat.

Q: Can Claude Desktop use Firecrawl to bypass Cloudflare protection?

Yes, the scrapepage tool handles modern anti-bot systems automatically. When Claude Desktop requests a protected page, the remote server processes the JS challenges and returns clean Markdown.

Q: How does the Firecrawl MCP server handle long site crawls in Claude Desktop?

The crawlsite tool runs asynchronously to prevent your chat session from timing out. It returns a job ID, allowing Claude Desktop to check back periodically until the site extraction completes.

Q: What is the difference between mapsite and searchweb?

mapsite extracts the URL structure of a single domain to build a sitemap. In contrast, searchweb queries search engines and returns scraped Markdown content from the top organic results.

Feed clean Markdown straight to Claude Desktop from any URL without leaving your chat window.

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 Claude Desktop

Create your Vinkius account to connect Firecrawl to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn messy sites into Claude Desktop markdown inputs

`scrape_page` extracts clean Markdown from any URL and hands it directly to your chat window. The tool strips out cookie banners, navigation menus, and tracking scripts so your agent reads only the core content. You feed a raw URL to Claude Desktop, and the MCP server handles the dynamic Javascript execution. This means you bypass anti-bot walls without writing custom scraping scripts or managing headless browsers locally.

Map site architectures directly in your chat

`map_site` returns a clean list of discovered URLs for any domain you target. Your agent uses this sitemap to understand how a documentation hub or blog is organized before pulling specific pages. Instead of guessing page paths, you let Claude Desktop analyze the structure first. This prevents your agent from requesting broken links or wasting your API limits on useless pages.

Run deep recursive crawls through Claude Desktop

`crawl_site` starts an asynchronous crawl across an entire target website to convert every page into structured Markdown. The MCP server returns a job ID immediately so your local Claude Desktop client doesn't freeze during long operations. Your agent tracks the job progress in the background while you keep typing. Once finished, you get a clean dataset of the entire site's documentation ready for analysis.

Setup guide

Set up Firecrawl MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Firecrawl MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Firecrawl MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under firecrawl-mcp.

json

{
  "mcpServers": {
    "firecrawl-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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Save the file and restart your Claude Desktop app to make the web scraping tools available in your chat.

Yes, the `scrape_page` tool handles modern anti-bot systems automatically. When Claude Desktop requests a protected page, the remote server processes the JS challenges and returns clean Markdown.

The `crawl_site` tool runs asynchronously to prevent your chat session from timing out. It returns a job ID, allowing Claude Desktop to check back periodically until the site extraction completes.

`map_site` extracts the URL structure of a single domain to build a sitemap. In contrast, `search_web` queries search engines and returns scraped Markdown content from the top organic results.

Your scraped page content and target URLs flow directly through the secure Vinkius proxy to the Firecrawl API. No raw text or target URLs are stored permanently on the Vinkius platform.

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