How to Use the Browserhub MCP in Claude Code

Q: How do I add the Browserhub MCP server to Claude Code?

Run the command claude mcp add --transport http browserhub -- in your terminal. This registers the server in your local /.claude.json configuration file for instant headless access.

Q: Can I pipe the output of a Browserhub scrape in Claude Code?

Yes, Claude Code can execute directscrape and pipe the resulting text directly to other CLI tools. You can redirect the output to local files, grep for specific terms, or pass it to database scripts.

Q: How does Claude Code handle proxy routing with Browserhub?

The agent uses the MCP standard to call listproxylocations and choose an exit node before running a scrape. This ensures your automated terminal pipelines bypass regional blocks by routing requests through the correct gateway.

Q: Can I check my Browserhub credit balance within Claude Code?

The agent calls getaccountbalance to print your remaining credit balance. This allows you to monitor API costs directly from your terminal session before kicking off heavy extraction pipelines.

Run web scrapers and pipeline clean data directly into your terminal using 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 Browserhub MCP to Claude Code

Create your Vinkius account to connect Browserhub 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 Browserhub with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Command-line scraping with this headless MCP Server

Running the `direct_scrape` tool extracts raw text from any URL directly from your shell. Claude Code runs this tool to pipe documentation or configuration files straight into your local command-line tools. You don't need a browser to fetch web content anymore. The terminal agent handles the entire request-response cycle and outputs pure text ready for grep or awk processing.

Automate cron jobs and scraper runs

Launching structured scraping tasks on a schedule is done via the `run_scraper` tool. Claude Code chains this command with your local shell scripts to automate daily data pipelines. The agent monitors progress in the background by calling `get_scraping_job`. Once the extraction completes, the raw output pipes directly into your database ingestion script.

Manage scraper schemas from your terminal

Viewing your configured data extractors without a web dashboard is fast with the `list_blueprints` tool. Claude Code lists these templates over the active MCP link to let you choose the correct parser for your automated pipeline. If an extraction fails, the agent calls `get_blueprint` to output the selector schema. This lets you inspect the target elements and update your shell scripts to handle layout changes.

Setup guide

Set up Browserhub 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 browserhub-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http browserhub-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 Browserhub 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": {
    "browserhub-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 Browserhub. 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 Browserhub 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 Browserhub MCP in Claude Code

Run the command `claude mcp add --transport http browserhub -- ` in your terminal. This registers the server in your local ~/.claude.json configuration file for instant headless access.

Yes, Claude Code can execute `direct_scrape` and pipe the resulting text directly to other CLI tools. You can redirect the output to local files, grep for specific terms, or pass it to database scripts.

The agent uses the MCP standard to call `list_proxy_locations` and choose an exit node before running a scrape. This ensures your automated terminal pipelines bypass regional blocks by routing requests through the correct gateway.

The agent calls `get_account_balance` to print your remaining credit balance. This allows you to monitor API costs directly from your terminal session before kicking off heavy extraction pipelines.

Vinkius executes all Browserhub requests inside isolated, short-lived V8 sandboxes. Your scraping queries and target URLs are never cached on the host, ensuring your terminal pipelines remain secure and private.

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