How to Use the Browserless MCP in LlamaIndex

Q: How does Browserless feed data into a LlamaIndex vector store?

The server pulls live HTML using getpagecontent, which LlamaIndex then parses into Document nodes. These nodes are embedded and stored in your vector database for semantic search.

Q: Can LlamaIndex trigger custom scraping scripts in Browserless?

Yes, you can use runscrape to run custom Javascript on the target page. This allows your agent to extract clean, structured data before indexing it.

Q: How do I monitor my Browserless usage?

Your agent can call getusagestats to check your current plan consumption using the MCP Server. This helps you throttle indexing jobs before hitting your monthly limits.

Q: What happens if a session hangs during a LlamaIndex indexing run with Browserless?

You can run listactivesessions to identify stuck browser instances. The agent can then terminate or ignore them to keep the ingestion pipeline moving.

Turn live web pages into searchable vector indexes using Browserless with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Browserless 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 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding RAG pipelines with live web data

The `get_page_content` tool fetches fully rendered HTML from any URL to feed your LlamaIndex documents. This ensures your vector store index gets clean, client-side rendered text instead of broken scripts or empty tags. Your agent calls this tool dynamically when a user query requires fresh web data. The retrieved text is instantly chunked, embedded, and indexed to ground the response in real-time facts.

Archiving documents with this Browserless MCP Server

The `generate_pdf` tool converts target web resources into static PDF files for long-term storage. LlamaIndex ingestion pipelines read these PDFs to build a permanent, searchable knowledge base of offline documentation. For visual indexing, `take_screenshot` captures the layout of the page. This lets you index visual elements alongside the raw text for multimodal retrieval models.

Custom script execution for deep indexing

The `run_scrape` tool executes custom scripts to extract specific data structures from complex web applications. Instead of generic page grabs, your indexer targets precise JSON payloads or nested tables. To avoid running blind, `check_system_health` monitors the connection status before starting a massive indexing job. It ensures your pipeline doesn't waste tokens on dead endpoints.

Setup guide

Set up Browserless 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 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 tools.",
)
response = await agent.run("List recent Browserless 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 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 LlamaIndex

The server pulls live HTML using `get_page_content`, which LlamaIndex then parses into Document nodes. These nodes are embedded and stored in your vector database for semantic search.

Yes, you can use `run_scrape` to run custom Javascript on the target page. This allows your agent to extract clean, structured data before indexing it.

Your agent can call `get_usage_stats` to check your current plan consumption using the MCP Server. This helps you throttle indexing jobs before hitting your monthly limits.

You can run `list_active_sessions` to identify stuck browser instances. The agent can then terminate or ignore them to keep the ingestion pipeline moving.

Every target URL and generated PDF is processed inside an isolated, short-lived V8 sandbox. Vinkius enforces a strict zero-trust model, meaning your source data is never cached or exposed to third parties.

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