How to Use the BrowserStack MCP in LangChain

Q: Can a LangChain agent delete failed runs on BrowserStack automatically?

Yes, the agent can invoke deletebuild or deletesession based on conditional logic in your chain. You write the rules in your agent prompt to purge specific runs when they meet your cleanup criteria.

Q: How does LangSmith trace BrowserStack tool calls made by my LangChain agent?

Every time your agent calls a tool like getbuild, the adapter logs the inputs and outputs to LangSmith. You trace the exact latency, token count, and raw JSON payload of every automation query.

Q: Can I run parallel test evaluations with this setup?

You run parallel evaluations by chaining getplan checks with your execution loops. The agent monitors queued sessions in real-time to avoid hitting concurrency limits.

Run multi-step browser testing chains in LangChain using this MCP Server to fetch direct BrowserStack execution data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrowserStack MCP to LangChain

Create your Vinkius account to connect BrowserStack 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 BrowserStack with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate test triage with LangChain agents

The BrowserStack MCP Server exposes tools to inspect and manage your automation pipeline directly from your LLM chains. Your agent starts by calling `list_projects` to locate the target suite, then pulls recent executions with `list_builds` to isolate failures. Instead of manually clicking through dashboards, your runtime feeds these build statuses directly into the next step of your chain. You get immediate, programmatic triage of failing test suites based on real-time API responses.

Deep session debugging and log extraction

Debugging broken test steps requires raw execution data, which you fetch using `get_session_logs` and `get_session`. The agent analyzes the exact reasons behind a test failure by parsing the text execution logs and metadata. By passing this output to a LangSmith-monitored chain, you trace exactly how the agent diagnosed the bug. You see the inputs, the raw log output, and the final summary in one execution graph.

Real-time capacity and environment checking

Before kicking off a massive test suite, your agent uses `get_plan` to inspect your current parallel session usage. If the queue is full, the agent waits or alerts the team instead of triggering a bottleneck. It cross-references these limits with supported environments via `list_browsers` to verify your target configurations exist. This prevents wasted runs and keeps your execution budget under control.

Setup guide

Set up BrowserStack 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 BrowserStack 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({
    "browserstack-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 BrowserStack 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 BrowserStack. 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 BrowserStack 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 BrowserStack MCP in LangChain

You configure the credentials on the Vinkius platform when provisioning the server. The LangChain agent receives a single secure endpoint token, so your raw BrowserStack API keys never expose themselves in your local code or agent logs.

Yes, the agent can invoke `delete_build` or `delete_session` based on conditional logic in your chain. You write the rules in your agent prompt to purge specific runs when they meet your cleanup criteria.

Every time your agent calls a tool like `get_build`, the adapter logs the inputs and outputs to LangSmith. You trace the exact latency, token count, and raw JSON payload of every automation query.

You run parallel evaluations by chaining `get_plan` checks with your execution loops. The agent monitors queued sessions in real-time to avoid hitting concurrency limits.

Your session logs, build metadata, and video URLs are processed in memory within an ephemeral V8 sandbox. No persistent storage of these logs occurs on the hosting platform, keeping your proprietary test data completely 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