How to Use the Cloud BOT MCP in Mastra AI

Q: How does Mastra AI recover when a Cloud BOT execution fails?

The workflow engine catches errors from executebot and applies your configured backoff strategy. If the bot still fails, the agent uses listjobs to diagnose the crash and route the failure to your error handler.

Q: Can I require human approval before Mastra AI triggers a bot?

Yes, configure Mastra's tool approval middleware on the executebot tool. This pauses the agent and waits for your manual confirmation before launching the cloud browser.

Build resilient, self-healing browser automation workflows using the Mastra AI agent engine and Cloud BOT.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloud BOT MCP to Mastra AI

Create your Vinkius account to connect Cloud BOT 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 Cloud BOT with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build self-healing browser runs with this MCP Server

This MCP Server embeds scriptless browser automation into your TypeScript workflow pipelines. Your Mastra AI agents use `execute_bot` to scrape sites, relying on Mastra's built-in retry engine to handle network hiccups or temporary site blocks. If a run fails after multiple attempts, the workflow triggers conditional logic based on the failure code. The agent automatically switches to a backup bot or alerts an admin, preventing silent failures in your data pipelines.

Track automation jobs across Mastra AI steps

This MCP Server lets you monitor asynchronous browser tasks within complex multi-step agents. Your Mastra AI worker polls the status of active runs using `get_job_status` before proceeding to downstream processing steps. If a job gets stuck in an infinite loop on a broken website, your agent invokes `cancel_job` to free up resources. The workflow then logs the error and moves to the next item in the execution queue.

Process scraped files inside Mastra AI pipelines

This MCP Server exposes remote file outputs directly to your workflow steps. Your Mastra AI agent inspects downloaded assets using `list_cloudbot_files` to verify the scraper actually captured the target documents. The agent feeds these verified file paths into your data ingestion tools for parsing. This ensures your database only receives clean, complete data from successful browser runs.

Setup guide

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

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

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

Instantiate the client using the Vinkius URL and spread the tools returned by `listTools` into your agent configuration. The framework automatically registers operations like `execute_bot` for use in your workflows.

Yes, you run the job asynchronously and use a workflow step to poll `get_job_status`. This keeps your main execution thread open while the browser task runs in the cloud.

The workflow engine catches errors from `execute_bot` and applies your configured backoff strategy. If the bot still fails, the agent uses `list_jobs` to diagnose the crash and route the failure to your error handler.

Yes, configure Mastra's tool approval middleware on the `execute_bot` tool. This pauses the agent and waits for your manual confirmation before launching the cloud browser.

The agent never manages your browser login details or target site credentials directly. Vinkius handles the authorization token securely, keeping your sensitive automation inputs isolated from the agent's execution environment.

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