How to Use the Browserless (Playwright Cloud) MCP in Claude Code

Q: How do I add the Browserless (Playwright Cloud) MCP Server to my Claude Code CLI?

Run the command claude mcp add --transport http browserless -- directly in your terminal. This registers the server in your /.claude.json configuration file, allowing Claude Code to run Playwright tasks instantly.

Q: How does Claude Code handle slow-loading single-page apps using the Browserless (Playwright Cloud) MCP Server?

The agent calls scrapewithwait to hold the connection until specific CSS selectors are fully rendered. This prevents your terminal scripts from receiving empty HTML wrappers or incomplete DOM states.

Q: Can I execute complex DOM interactions from the terminal?

Yes, you can command the agent to use runcustomfunction to execute custom JavaScript directly inside the remote browser. This allows you to trigger clicks, fill out forms, or scrape dynamic states programmatically.

Pipe raw HTML, screenshots, and PDFs from a remote Playwright cloud browser directly into your Claude Code terminal sessions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless (Playwright Cloud) MCP to Claude Code

Create your Vinkius account to connect Browserless (Playwright Cloud) 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 Browserless (Playwright Cloud) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Scraping inside the Claude Code Terminal

The `get_html_content` tool pulls raw markup from any public or private URL directly into your terminal stdout. Claude Code uses this tool to inspect server responses, audit live production pages, and feed raw HTML into local shell pipelines. Because you are working purely in the CLI, this MCP Server acts as your terminal's visual eyes. It lets your agent fetch live web context without needing to open a heavy desktop browser.

Automated PDF and Screenshot Pipeline Exports

Generating binary files of remote web pages is handled by `get_pdf` and `get_screenshot` tools, saving them directly to your local workspace. Claude Code invokes these tools during terminal audits to generate rapid visual records of deployment states. If you are running CI/CD checks, the agent can trigger these tools to document frontend regressions automatically. You get clean visual assets saved directly to your repository without running a local X11 server.

Proxy Routing and Stealth Evasion via CLI

Routing your browser instances through clean proxies is done via `scrape_with_proxy` and `scrape_with_stealth` to avoid terminal IP bans. Claude Code uses these tools to scrape documentation and API schemas from rate-limited developer portals. This setup ensures your automated scripts do not get blocked by cloud firewalls mid-execution. Your terminal agent maintains uninterrupted access to the external web resources it needs to diagnose system issues.

Setup guide

Set up Browserless (Playwright Cloud) 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 browserless-playwright-cloud-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Browserless (Playwright Cloud) transactions." It will automatically discover and invoke the available Browserless (Playwright Cloud) tools.

Terminal

claude mcp add --transport http browserless-playwright-cloud-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 Browserless (Playwright Cloud) 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": {
    "browserless-playwright-cloud-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 Playwright Cloud. 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 Browserless (Playwright Cloud) 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 Browserless (Playwright Cloud) MCP in Claude Code

Run the command `claude mcp add --transport http browserless -- ` directly in your terminal. This registers the server in your `~/.claude.json` configuration file, allowing Claude Code to run Playwright tasks instantly.

Yes, since Claude Code runs entirely in the terminal, it can execute the remote browser tools within GitHub Actions or Docker containers. The server handles all heavy browser rendering in the cloud, requiring zero local GUI dependencies.

The agent calls `scrape_with_wait` to hold the connection until specific CSS selectors are fully rendered. This prevents your terminal scripts from receiving empty HTML wrappers or incomplete DOM states.

Yes, you can command the agent to use `run_custom_function` to execute custom JavaScript directly inside the remote browser. This allows you to trigger clicks, fill out forms, or scrape dynamic states programmatically.

All network traffic, target URLs, and generated PDFs are processed inside secure, single-use V8 isolates managed by Vinkius. No data is cached or written to persistent storage, ensuring your internal URLs and scraped markup remain completely 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