How to Use the Browse AI MCP in LangChain

Q: How do I check my scraping limits inside a LangChain run?

You can call the listcredits tool directly from your agent to inspect your remaining Browse AI balance. This prevents your chain from starting expensive bulk runs when credits are too low.

Q: How does LangChain parse the JSON returned by Browse AI?

The gettaskdata tool returns pre-parsed JSON that fits right into your LangChain document structures. Your agent reads the keys directly, bypassing the need for manual regex or BeautifulSoup parsing.

Feed live scraped web data directly into your LangChain reasoning loops using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to LangChain

Create your Vinkius account to connect Browse AI 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 Browse AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic Multi-Step Web Scraping

The `run_robot` tool lets your LangChain agent trigger a Browse AI scraper on any URL it encounters during a run. This tool turns raw web pages into structured JSON data that your agent can immediately pass to the next step in its chain. If the agent needs to check the extraction status, it uses this MCP Server to query `get_task` or `get_task_data` to pull the final payload. You get clean, predictable inputs for your downstream LLM steps, tracked end-to-end via LangSmith.

Parallel Bulk Extraction Chains

The `run_bulk_task` tool runs multiple scraping jobs concurrently across a list of target URLs. Your chain can feed a list of competitor sites or product pages directly into this tool and wait for the batch to complete. Once finished, the agent calls `download_bulk_data` to pull the entire dataset into memory. You can then map this array over a summarization or analysis chain in LangChain without worrying about rate limits or browser blocks.

Intelligent Site Monitoring

The `list_monitors` tool exposes your active Browse AI monitoring tasks directly to your agent's MCP context. This lets your chain check which web pages are currently being watched for layout or content changes. Your agent can inspect these configurations using `get_robot` to decide if it needs to deploy a new monitor or adjust an existing one. It turns passive scraping setups into an active, self-correcting data collection pipeline.

Setup guide

Set up Browse AI 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 Browse AI 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({
    "browse-ai-1-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 Browse AI 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 Browse AI. 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 Browse AI 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 Browse AI MCP in LangChain

You can call the `list_credits` tool directly from your agent to inspect your remaining Browse AI balance. This prevents your chain from starting expensive bulk runs when credits are too low.

Yes, your agent handles this by polling the task status. The chain triggers `run_robot`, gets a task ID, and then uses `get_task` in a loop until the status shows as successful.

The `get_task_data` tool returns pre-parsed JSON that fits right into your LangChain document structures. Your agent reads the keys directly, bypassing the need for manual regex or BeautifulSoup parsing.

It connects over standard Server-Sent Events (SSE) using the LangChain MCP adapter. This keeps your connection lightweight and lets you combine this server with other data sources in the same execution loop.

Your scraped JSON payloads and extraction parameters are processed in an ephemeral V8 sandbox. We never store the actual text or data extracted from target sites, keeping your target URLs and captured inputs fully isolated.

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