How to Use the Browserbear MCP in LangChain

Q: Does the Browserbear integration support LangSmith tracing?

Yes, every tool invocation like listruns or getrun is fully traced. You get deep visibility into execution latency and payload sizes directly in your LangSmith dashboard.

Q: Can I run multiple browser tasks in parallel?

You can. Your agent can trigger several runs using runtask and then poll their status using getrun concurrently to speed up data collection.

Build LangChain agents that run browser tasks and grab screenshots on the fly with this 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 Browserbear MCP to LangChain

Create your Vinkius account to connect Browserbear 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 Browserbear with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Browser Runs Directly into LangChain Agents

The Browserbear MCP Server gives your ReAct agents the ability to run browser tasks dynamically. When an agent needs fresh data, it hits `run_task` and waits for the payload. You don't have to build custom API wrappers anymore. The agent checks the status with `get_run`, grabs the raw scraped output, and feeds it straight to the next LLM call in your chain.

Debug Automation Pipelines via LangSmith Tracing

Debugging browser tasks with this MCP Server is straightforward when you hook up LangSmith tracing. Every call to `take_screenshot` or `create_task` shows up in your tracing dashboard. You see the exact latency, token count, and raw payload returned by the Browserbear API. If a selector changes on a target site, your agent catches the failure in real time by checking `get_task`.

Monitor Account Usage and Project States Dynamically

This MCP Server lets your agents monitor account usage and project states dynamically. Keep your automated workflows from burning through your budget by checking credits first. Your agent can call `get_account_usage` before kicking off a heavy batch of jobs to make sure you have enough credits. It can also query `list_projects` and `list_tasks` to route workloads to the correct browser templates.

Setup guide

Set up Browserbear 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 Browserbear 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({
    "browserbear-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 Browserbear 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 Browserbear. 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 Browserbear 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 Browserbear MCP in LangChain

Vinkius manages the API keys for you. You only need to configure the MultiServerMCPClient with your Vinkius endpoint token, and your agent gets access to `run_task` instantly.

Yes. The agent evaluates the user prompt, determines if it needs fresh web data, and invokes `run_task` or `take_screenshot` based on its reasoning loop.

Yes, every tool invocation like `list_runs` or `get_run` is fully traced. You get deep visibility into execution latency and payload sizes directly in your LangSmith dashboard.

You can. Your agent can trigger several runs using `run_task` and then poll their status using `get_run` concurrently to speed up data collection.

All screenshots, task configurations, and run metadata pass through an isolated V8 sandbox. Your credentials and scraped payloads are never stored on Vinkius servers, keeping your web automation data completely 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