How to Use the Browse AI MCP in LangChain

Q: How do I handle Browse AI rate limits inside a LangChain loop?

Use getsystemstatus inside your chain's decision node. Your LangChain agent can read the queue status and delay the next runrobot call if the API is congested.

Q: Can I trace Browse AI tool outputs using LangSmith?

Yes. Every time your LangChain agent calls gettask or listrobots, LangSmith logs the exact JSON payload. This gives you full visibility into extraction latency and token costs.

Q: How do I configure the Browse AI MCP server in LangChain?

Install langchain-mcp-adapters, initialize the client, and call client.gettools(). Pass these tools to your agent constructor to let it run scraping tasks dynamically.

Q: Can my agent create new scraper schedules?

Yes, using the createmonitor tool. Your agent can set up recurring scraping schedules for any robot it finds via listrobots.

Run Browse AI scraping robots directly inside your LangChain reasoning loops to feed real-time web data to downstream chains.

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

Chain web extraction with downstream actions

The `run_robot` tool lets your LangChain agent trigger automated web scraping tasks on demand. Your chain can kick off an extraction job, wait for the status with `get_task`, and immediately pass that raw structured data to the next prompt template or database writer in your pipeline. Because LangChain tracks execution step-by-step, every web run shows up inside LangSmith. You see exactly how much latency `get_task` introduces and what payload your scraper returned before it hit your next LLM node.

Observe scraping queues across multiple servers

The `get_system_status` tool provides your LangChain agent with real-time queue health and API limits before launching heavy jobs. This prevents your multi-step chains from stalling when external web scrapers are backed up. Using this MCP Server with `MultiServerMCPClient` allows your agent to route tasks dynamically. If Browse AI is busy, the chain pivots to alternative data sources in your agentic workflow.

Manage bulk extraction runs in LangGraph

The `list_bulk_runs` tool gives LangChain agents the ability to audit historical extraction batches. Your agent uses this tool to check if a specific dataset already exists before spinning up a new robot. By running this MCP Server, your graph avoids duplicate scraping bills. The agent simply pulls the cached run data and feeds it straight to your vector store.

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-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

Use `get_system_status` inside your chain's decision node. Your LangChain agent can read the queue status and delay the next `run_robot` call if the API is congested.

Yes. Every time your LangChain agent calls `get_task` or `list_robots`, LangSmith logs the exact JSON payload. This gives you full visibility into extraction latency and token costs.

Install `langchain-mcp-adapters`, initialize the client, and call `client.get_tools()`. Pass these tools to your agent constructor to let it run scraping tasks dynamically.

Yes, using the `create_monitor` tool. Your agent can set up recurring scraping schedules for any robot it finds via `list_robots`.

Yes. Your extracted web data and robot configurations never touch third-party logging servers. The Vinkius sandbox runs the MCP connection in an isolated V8 environment, keeping your API keys and scraped payloads strictly private.

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