How to Use the Crawlbase MCP in Claude

Q: How do I install the Crawlbase MCP server in Claude Desktop?

Edit your claudedesktopconfig.json file. Add the Crawlbase server details under the mcpServers key, then restart the application. You can also use the Extensions UI for a one-click install if available.

Q: Does Crawlbase work with Claude Desktop's local file access?

It does. Claude can pull live data from scrapehtml, format it, and write the output directly to a local CSV file on your machine. You get end-to-end data pipelines in a single chat.

Connect Claude Desktop to Crawlbase and extract raw HTML, JS-rendered DOMs, or social profiles straight into your chat.

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 Claude Desktop

Create your Vinkius account to connect Crawlbase 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 Crawlbase with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse raw HTML and JS-rendered pages via MCP Server

`scrape_html` pulls unstyled DOM nodes from any public URL directly into Claude Desktop. You hand it a target link, and the server routes the request through datacenter proxies to bypass basic blocking. If the target relies on client-side frameworks, `scrape_js_rendered` loads the page in a headless browser first. The engine waits for network idle states before handing the final DOM back to your chat session, letting you analyze dynamic content without writing a custom puppeteer script.

Extract structured profiles and product catalogs

`scrape_amazon` returns parsed ASINs, pricing tiers, and review counts instead of raw markup. You ask Claude to compare three product pages, and the server handles the specific pagination and anti-bot constraints native to that storefront. The same structural extraction applies to social networks. Using `scrape_linkedin`, `scrape_facebook`, and `scrape_twitter`, your AI agent reads mapped profile attributes and timeline arrays. You get clean JSON data back instead of fighting rate limits.

Generate custom payloads and visual snapshots

`custom_scrape` lets you define exact proxy headers, geo-targeting rules, and request payloads for complex endpoints. You dictate the exact parameters Claude sends to the target server. Sometimes you need visual proof that a page rendered correctly. The `get_screenshot_link` tool captures a full-page image of the target domain and drops the URL right in your conversation. It confirms layout shifts or ad placements visually before you commit to parsing the text.

Setup guide

Set up Crawlbase 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 Crawlbase 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 Crawlbase 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 crawlbase-mcp.

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 Claude Desktop

Edit your claude_desktop_config.json file. Add the Crawlbase server details under the mcpServers key, then restart the application. You can also use the Extensions UI for a one-click install if available.

Yes. Go to Settings, find Integrations, and add a custom connector. Paste your remote Crawlbase MCP Server HTTPS URL there to start querying live sites from your browser.

You skip the infrastructure setup. Instead of managing proxy pools and headless browsers, you just ask Claude to read a URL. The server handles CAPTCHAs and JS rendering automatically.

It does. Claude can pull live data from scrape_html, format it, and write the output directly to a local CSV file on your machine. You get end-to-end data pipelines in a single chat.

The system only processes the specific URLs and parameters you feed to tools like scrape_twitter or scrape_amazon. Vinkius runs this MCP integration inside a V8 isolate sandbox, meaning your target endpoints and extracted DOM strings vanish the moment the extraction completes. No long-term storage exists.

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