How to Use the Crawlbase MCP in Claude Code

Q: How do I add Crawlbase to Claude Code from the command line?

Run claude mcp add --transport http crawlbase-mcp -- in your terminal. Claude Code will verify the connection and list the available scraping tools.

Q: Can I pipe Crawlbase search results to other CLI tools using Claude Code?

Yes, Claude Code can execute scrapegoogleserp and pipe the clean search arrays directly to standard output or local text files. This makes it perfect for terminal-based data pipelines.

Q: Can I run automated headless screenshot checks with Claude Code?

Yes, Claude Code calls getscreenshotlink to generate validation links for web domains. You can use these links in CI/CD pipelines to verify site availability.

Pipe headless web scraping payloads and raw HTML directly into your terminal workflows using Crawlbase and Claude Code.

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 Code

Create your Vinkius account to connect Crawlbase to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-Driven Scraping Pipelines with Claude Code

The `scrape_html` tool routes web requests through Crawlbase datacenter proxies to return raw markup directly to your terminal. Claude Code executes this command using the MCP server, pipes the resulting HTML into local CLI utilities, or saves it directly to raw log files. This headless setup allows you to run complex web extractions from SSH sessions or bash scripts. You can filter the raw markup, run grep commands, or feed the data into local build processes with zero GUI overhead.

Parsing JSON Payloads Headless via MCP Server

The `scrape_json_format` tool extracts structured properties and active fields from target web pages, returning clean JSON to your shell environment. Claude Code processes this structured data instantly, allowing you to run automated validation checks on remote APIs. You can script this tool to monitor live endpoints or track data changes over time. The terminal agent handles tool execution, reformats the JSON output, and appends the clean data to your terminal-based databases.

Automated Social Data Extraction via CLI

The `scrape_twitter` tool pulls mapped data limits from X profiles using the Crawlbase extraction engine. Claude Code triggers this tool from the command line, parses the user feed, and outputs clean structured text directly to stdout. By combining this with `scrape_linkedin`, you can build automated CLI scripts to track professional updates and social changes. Our command line agent runs these tools sequentially, formats the terminal output, and prepares it for automated reporting scripts.

Setup guide

Set up Crawlbase MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see crawlbase-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Crawlbase transactions." It will automatically discover and invoke the available Crawlbase tools.

Terminal

claude mcp add --transport http crawlbase-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "crawlbase-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http crawlbase-mcp -- ` in your terminal. Claude Code will verify the connection and list the available scraping tools.

Yes, Claude Code can execute `scrape_google_serp` and pipe the clean search arrays directly to standard output or local text files. This makes it perfect for terminal-based data pipelines.

No, the Crawlbase MCP server manages all proxy rotation and CAPTCHA solving automatically. Claude Code receives the final scraped HTML or JSON payload without any extra configuration flags.

Yes, Claude Code calls `get_screenshot_link` to generate validation links for web domains. You can use these links in CI/CD pipelines to verify site availability.

Vinkius runs the server in an isolated V8 sandbox, meaning your raw HTML data and API credentials are never cached on disk. All network requests are routed ephemerally through secure channels.

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