How to Use the Bright Data MCP in LangChain

Q: Can I monitor the cost of Bright Data requests inside LangChain?

Yes. Every time your chain calls sendrequest, LangSmith logs the tool payload and execution time. You can match these logs against your account metrics by running getaccountstatus to track usage.

Q: How does this server secure my zone passwords and scraping configurations?

All sensitive credentials fetched via getzonepasswords remain inside Vinkius's isolated sandbox. They are never sent to external LLM providers or logged in plain text.

Feed live web scrapers and unblocked search results directly into your LangChain reasoning pipelines without managing proxy pools.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run unblocked web searches inside your chains

`send_request` lets your LangChain agent query the Search Engine Research Page (SERP) API or Web Unlocker directly when it needs real-time data. Your agent executes this tool to bypass anti-bot systems, feeding raw, structured search results straight into the next link of your chain. You do not need to write custom scraper code or handle IP rotation. By combining this tool with LangSmith, you track the exact latency and token usage of every unblocked request your agent makes.

Control scraping browsers from LangGraph agents

`list_browser_sessions` gives your agent the power to monitor active Scraping Browser instances on the fly. When a multi-step pipeline gets stuck, the agent checks these sessions to see where the scraper stalled. This MCP Server exposes browser management directly to your runtime. You can build self-healing scraping loops that spin up, check, and teardown remote browser sessions based on real-time feedback.

Collect dataset snapshots on autopilot

`trigger_dataset` starts a custom web crawling job directly from your LangChain execution path. Your agent triggers the collection, polls `get_dataset_progress` to check the status, and fetches the final data once ready. This setup turns slow, manual data collection into an automated background step in your agentic workflows. The agent handles the waiting, while you focus on processing the structured output.

Setup guide

Set up Bright Data 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 Bright Data 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({
    "bright-data-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 Bright Data 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 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 LangChain

You do not have to manage credentials manually in your chain. The MCP Server handles zone authentication behind the scenes, letting your agent call `get_zone_passwords` to grab proxy credentials dynamically when executing requests.

Yes. Every time your chain calls `send_request`, LangSmith logs the tool payload and execution time. You can match these logs against your account metrics by running `get_account_status` to track usage.

The server passes API status codes directly to your agent. If a rate limit occurs, your ReAct loop detects the error and can back off or switch zones using `get_all_zones` before retrying the step.

No. A single connection to this MCP integration exposes both the Scraping Browser and the Crawl API tools directly to your agent.

All sensitive credentials fetched via `get_zone_passwords` remain inside Vinkius's isolated sandbox. They are never sent to external LLM providers or logged in plain text.

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