How to Use the BrowserStack MCP in Mastra AI

Q: Can I use BrowserStack and Mastra AI to trigger retries?

You can build a workflow in Mastra AI that calls listbuilds and triggers a new run if a previous one failed. It handles the retry logic for you.

Build complex Mastra AI workflows that automatically debug and clean up BrowserStack test environments.

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 Mastra AI

Create your Vinkius account to connect BrowserStack to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Mastra AI testing workflows

Mastra AI agents can now trigger `list_builds` and `get_project` to evaluate test health. If a project shows failing builds, the agent flags it for review. It removes the need for manual oversight. You define the logic, and the agent executes the cleanup or reporting steps based on real-time data.

Debugging BrowserStack with Mastra AI

Use `get_session` to pull detailed browser metadata when a test fails. Mastra AI agents parse these logs to identify the exact OS or browser causing the issue. This creates a feedback loop. Your agent identifies the failure and provides the logs you need to fix the bug immediately.

Scaling BrowserStack via Mastra AI

Mastra AI monitors your concurrency limits by calling `get_plan` before kicking off new test suites. It prevents queueing by verifying availability first. This keeps your automation running at peak efficiency. The agent manages your project throughput without human intervention.

Setup guide

Set up BrowserStack MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All BrowserStack tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "browserstack-mcp-client",
  servers: {
    "browserstack-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "BrowserStack Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to BrowserStack tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent BrowserStack transactions"
);
console.log(result.text);

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 Mastra AI

The server exposes tools that your Mastra AI agent calls during a workflow. It acts as the bridge between your test infrastructure and your agent's decision engine.

You can build a workflow in Mastra AI that calls `list_builds` and triggers a new run if a previous one failed. It handles the retry logic for you.

Only the test results, session IDs, and log URLs you request are fetched. Your agent handles this data within your local execution environment.

Data is transmitted over encrypted channels using your endpoint token. The MCP server does not store any of your BrowserStack session information.

The agent only sees build statuses, session logs, and plan capacity. It treats this information as ephemeral data for the duration of the workflow.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.