How to Use the Bright Data MCP in LlamaIndex

Q: Can I use Bright Data to feed real-time search results into LlamaIndex?

Yes. Your agent can run sendrequest to pull unblocked search results, then immediately convert those JSON payloads into Document objects for real-time querying.

Q: How does this Bright Data MCP Server prevent stale data in LlamaIndex?

The agent uses getdatasetprogress to check if a web crawl is finished. Once complete, it triggers an index update, ensuring your vector store always has the latest snapshot.

Q: Is it possible to manage proxy zones directly from LlamaIndex?

Yes. The MCP integration lets your agent query getzoneinfo to check proxy health and bandwidth limits, ensuring your data ingestion jobs do not run out of balance.

Q: Can I filter which MCP tools are exposed to my query engine?

Yes, you can use LlamaIndex's allowedtools filter to expose only the specific dataset or proxy tools your agent needs for a particular task.

Q: How is my extracted dataset and session data protected?

Raw dataset snapshots pulled via getdatasetsnapshot are processed locally within your secure runtime. The server does not cache or store your extracted web data on external servers.

Index unblocked web data and marketplace datasets directly into LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bright Data MCP to LlamaIndex

Create your Vinkius account to connect Bright Data 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 Bright Data with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live web data straight into vector stores

`get_dataset_snapshot` downloads raw data dumps directly into your LlamaIndex ingestion pipeline. Your agent fetches these snapshots, parses them, and indexes the contents into a vector store for semantic search. Instead of querying static, outdated files, you build RAG applications grounded in fresh web data. The agent pulls the exact files it needs without manual downloads.

Discover and monitor web datasets dynamically

`list_datasets` lets your LlamaIndex agent search the Bright Data marketplace for available web data sources. The agent can evaluate what data is available and decide which collection to trigger. This MCP Server lets your agent wait until the data is fully cooked before indexing it into your local knowledge base.

Route queries through unblocked proxy zones

`get_all_zones` retrieves your active proxy configurations so your agent can choose the best route for web extraction. Your agent inspects zone details with `get_zone_info` to ensure it uses the right IP types for specific domains. This programmatic control prevents scraping failures during ingestion. The agent dynamically adjusts its connection parameters based on the target site's difficulty.

Setup guide

Set up Bright Data 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 Bright Data 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 Bright Data tools.",
)
response = await agent.run("List recent Bright Data 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 Bright Data. 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 Bright Data 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 Bright Data MCP in LlamaIndex

Yes. Your agent can run `send_request` to pull unblocked search results, then immediately convert those JSON payloads into Document objects for real-time querying.

The agent uses `get_dataset_progress` to check if a web crawl is finished. Once complete, it triggers an index update, ensuring your vector store always has the latest snapshot.

Yes. The MCP integration lets your agent query `get_zone_info` to check proxy health and bandwidth limits, ensuring your data ingestion jobs do not run out of balance.

Yes, you can use LlamaIndex's allowed_tools filter to expose only the specific dataset or proxy tools your agent needs for a particular task.

Raw dataset snapshots pulled via `get_dataset_snapshot` are processed locally within your secure runtime. The server does not cache or store your extracted web data on external 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