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

Q: What is the best way to handle SPA sites with this integration?

Have your agent call scrapewithjs to execute custom DOM actions like button clicks before reading the page. This ensures the indexer captures the final, fully rendered HTML state.

Index raw HTML, PDFs, and screenshots directly into your LlamaIndex vector stores using a cloud browser.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Convert live web pages into LlamaIndex documents

This MCP Server uses `get_html_content` to fetch raw page sources directly into your indexing pipeline so you don't waste time managing local drivers. You avoid local browser dependencies entirely while pulling fresh data for your vector store. Selecting specific elements is handled by `scrape_elements` to target exact CSS selectors and extract clean text chunks. Your agent parses the exact divs you need, ignoring headers and footers before indexing.

Bypass bot detection during index updates

The `scrape_with_stealth` tool runs specialized evasion plugins inside the cloud browser to fetch protected pages. Your LlamaIndex ingestion pipeline bypasses standard cloud blocks without failing. When dealing with dynamic layouts, the engine runs `scrape_with_wait` to ensure elements render before extraction. This guarantees that your vector index receives fully populated text rather than empty templates.

Capture and store visual layouts for RAG

The `get_screenshot` tool generates full-page images that your LlamaIndex multi-modal indexers can parse. You index visual layouts alongside raw text to build richer context for your search queries. If you need structured print layouts, the `get_pdf` tool converts pages into clean documents. These files feed directly into your PDF readers, keeping your knowledge base grounded in verified source layouts.

Setup guide

Set up Browserless (Playwright Cloud) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Browserless (Playwright Cloud) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Browserless (Playwright Cloud) tools.",
)
response = await agent.run("List recent Browserless (Playwright Cloud) data")

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 LlamaIndex

You initialize the tool spec using the Vinkius connection string and call `to_tool_list_async`. This exposes tools like `get_html_content` to your agent, which indexes the returned markup on the fly.

Yes, use the allowed tools filter during initialization to restrict your agent to specific operations like `scrape_elements`. This prevents the model from invoking expensive rendering functions when it only needs raw text.

The server operates statelessly by default, but you can pass custom cookies or use `send_custom_payload` to manage session tokens. This keeps your web queries authenticated across multiple index updates.

Have your agent call `scrape_with_js` to execute custom DOM actions like button clicks before reading the page. This ensures the indexer captures the final, fully rendered HTML state.

Yes, every connection to the remote browser runs through an isolated, single-use sandbox. Your scraped HTML, screenshots, and PDFs are piped directly to your local LlamaIndex environment and never stored on our servers.

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