How to Use the BugBug MCP in Mastra AI

Q: How do I handle a failed BugBug suite run in a Mastra AI workflow?

You configure a conditional step after calling runsuite. The workflow checks the status with getsuiterun, and if it fails, triggers a retry block or alerts your dev team.

Q: Can Mastra AI automatically whitelist BugBug IP addresses?

Yes. You can build a workflow that calls getips via the MCP Server, then passes those IPs to your infrastructure provider's API to keep your staging environment accessible.

Q: How does the human-in-the-loop feature work with BugBug and Mastra AI?

You can set requireToolApproval on critical tools like runsuite. This pauses the Mastra workflow and sends a Slack button to your QA lead before executing the browser tests.

Q: Can I fetch specific test details inside a Mastra agent?

Yes, the agent uses gettest to pull the exact steps and configuration of any browser test. It can then compare this against your local code changes to see if a selector was deleted.

Q: How does Mastra AI secure my test suite configuration data?

All project data and test definitions retrieved via listprojects remain inside Vinkius's zero-trust MCP sandbox. The workflow engine only receives the sanitized JSON outputs over an encrypted SSE connection.

Build automated QA workflows that run BugBug suites, handle failures with Mastra AI, and retry broken browser tests.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugBug MCP to Mastra AI

Create your Vinkius account to connect BugBug 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 BugBug with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate BugBug regression suites with Mastra AI workflows

Browser tests can fail due to temporary network hiccups. When you hook this MCP Server into Mastra AI, you can build workflows that trigger `run_test` and automatically retry if the run fails. Mastra's built-in backoff engine waits a few minutes before calling `get_test_run` again. If the second run still fails, the workflow branches. It can trigger `list_test_runs` to check if this is a systemic issue or just a flaky selector, then alerts your engineering team with the exact failure details.

Run conditional BugBug suites based on deployment health

Don't waste run minutes executing your entire test suite when only one service changed. Your Mastra AI agent uses `list_suites` to find the specific tests matching your modified directory. It then initiates `run_suite` only for the affected components, keeping your QA budget under control. Once triggered, the workflow monitors the suite with `get_suite_run`. If the suite fails, Mastra executes a conditional branch to rollback your staging environment and log the exact step that broke.

Update security groups dynamically using this MCP Server

BugBug runners change their source IPs occasionally, which blocks them from accessing private staging environments. This server provides the `get_ips` tool so your Mastra AI agent can fetch the current IP list on a cron schedule. The workflow takes these IPs and automatically updates your AWS or Cloudflare firewall rules. By automating this check, your automated browser tests never fail due to unexpected network blocks.

Setup guide

Set up BugBug 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 BugBug 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: "bugbug-mcp-client",
  servers: {
    "bugbug-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent BugBug 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 BugBug. 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 BugBug 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 BugBug MCP in Mastra AI

You configure a conditional step after calling `run_suite`. The workflow checks the status with `get_suite_run`, and if it fails, triggers a retry block or alerts your dev team.

Yes. You can build a workflow that calls `get_ips` via the MCP Server, then passes those IPs to your infrastructure provider's API to keep your staging environment accessible.

You can set `requireToolApproval` on critical tools like `run_suite`. This pauses the Mastra workflow and sends a Slack button to your QA lead before executing the browser tests.

Yes, the agent uses `get_test` to pull the exact steps and configuration of any browser test. It can then compare this against your local code changes to see if a selector was deleted.

All project data and test definitions retrieved via `list_projects` remain inside Vinkius's zero-trust MCP sandbox. The workflow engine only receives the sanitized JSON outputs over an encrypted SSE connection.

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