How to Use the Browserless MCP in LangChain

Q: How does this MCP Server handle multiple active browser sessions?

The listactivesessions tool lets your agent inspect and manage running browser instances. If a job hangs, the agent checks this list to clean up resources.

Run headless Chrome inside your LangChain pipelines to scrape data and take screenshots on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless MCP to LangChain

Create your Vinkius account to connect Browserless 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 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step web extraction with LangChain

The `get_page_content` tool pulls fully rendered HTML straight into your LangChain runnables. Your agent handles client-side rendering automatically, grabbing the exact DOM state instead of raw, unexecuted source code. You can chain this output directly into a parser. If a page fails to load, the agent spins up `list_active_sessions` to debug or retries with `run_scrape` to bypass basic blocks.

Visual validation using this Browserless MCP Server

The `take_screenshot` tool captures visual layouts of any URL during your chain execution. LangChain agents use this to verify UI states or feed the resulting image to a multimodal model for layout analysis. When you need document archives, `generate_pdf` writes the target page to a clean PDF file. This lets your pipeline build static reports on demand without leaving the execution graph.

Operational monitoring of your browser fleet

The `check_system_health` tool reports the current operational state of your headless browser instances. It keeps your agent from running heavy scripts when the service is down or overloaded. To keep tabs on your subscription, `get_usage_stats` and `get_account_config` fetch your raw usage numbers and active limits. LangChain monitors these metrics mid-run to prevent out-of-memory crashes or rate limits during large jobs.

Setup guide

Set up Browserless 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 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-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 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 Browserless. 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 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 MCP in LangChain

Install the langchain-mcp-adapters package and initialize the MultiServer MCP client with the Vinkius URL. Pass the tools directly to your agent constructor to let it call headless Chrome operations.

Yes, your agent can execute custom Puppeteer or Playwright code using the `run_scrape` tool. This lets you bypass basic paywalls or complex form submissions directly inside your chain.

The `list_active_sessions` tool lets your agent inspect and manage running browser instances. If a job hangs, the agent checks this list to clean up resources.

Latency depends on the target website's load time, but Vinkius hosts the server on fast V8 isolates to keep overhead near zero. You can trace every tool call using LangSmith to pinpoint slow pages.

Your scraped HTML content and target URLs are processed in an ephemeral, zero-trust V8 sandbox that wipes clean instantly. No web data, rendered PDFs, or session histories are ever written to persistent storage.

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