How to Use the Browserless (Playwright Cloud) MCP in LangChain

Q: Can LangChain handle proxy routing with this Browserless (Playwright Cloud) setup?

Yes, the agent calls scrapewithproxy to route requests through your specified proxy servers. This keeps your IP footprint clean while LangChain tracks the performance of each proxy node.

Q: What happens when Browserless (Playwright Cloud) encounters slow-loading elements in LangChain?

The agent invokes scrapewithwait to halt execution until a specific CSS selector appears. LangChain monitors this wait state, ensuring your sequential chains do not break on slow network responses.

Q: How do I debug custom browser payloads sent from my chain?

Use the sendcustompayload tool to test raw JSON configurations against the Browserless REST endpoint. LangSmith monitors these payload dispatches, mapping inputs to outputs in your tracing logs.

Let your LangChain agents run a cloud-managed browser to scrape and interact with heavy JavaScript sites.

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 LangChain

Create your Vinkius account to connect Browserless (Playwright Cloud) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject custom JS during LangChain runs

This MCP Server exposes the `run_custom_function` tool to let your chain execute raw JavaScript inside a remote Playwright instance. Your agent writes the script, sends it to the cloud browser, and gets the modified page state back instantly. It's that simple. LangChain traces this execution through LangSmith so you see the exact payload sent to the remote browser. When the agent uses `scrape_with_js` to click buttons before reading the DOM, you track the entire latency chain in your console.

Extract clean HTML from JS-heavy targets

The `get_html_content` tool retrieves raw source code from single-page applications so you don't have to configure local web drivers. Your pipeline feeds the resulting markup directly into your document loaders. If a site uses anti-scraping measures, the agent switches to `scrape_with_stealth` to bypass blocks. LangChain manages these transitions dynamically, routing the clean output straight to your parsing chains.

Generate visual assets inside LangChain loops

The `get_screenshot` tool captures full-page visual states of any URL directly from your agentic workflow. You get raw image data back to feed into multimodal models or save for visual verification. For document-heavy pipelines, the agent calls `get_pdf` to render print-ready layouts on the fly. This turns raw web data into clean, structured PDF documents that your next chain step can process.

Setup guide

Set up Browserless (Playwright Cloud) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Browserless (Playwright Cloud) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "browserless-playwright-cloud-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Browserless (Playwright Cloud) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter package and initialize the client using the Vinkius transport URL. Call `get_tools` on the adapter to fetch tools like `scrape_elements` and pass them straight to your agent constructor.

Yes, the agent calls `scrape_with_proxy` to route requests through your specified proxy servers. This keeps your IP footprint clean while LangChain tracks the performance of each proxy node.

The agent invokes `scrape_with_wait` to halt execution until a specific CSS selector appears. LangChain monitors this wait state, ensuring your sequential chains do not break on slow network responses.

Use the `send_custom_payload` tool to test raw JSON configurations against the Browserless REST endpoint. LangSmith monitors these payload dispatches, mapping inputs to outputs in your tracing logs.

All page content, PDFs, and screenshots remain inside the ephemeral V8 sandbox before returning to your local LangChain runtime. No raw HTML or scraped data is written to persistent disk 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