How to Use the Browse AI MCP in Mastra AI

Q: How do I register the Browse AI MCP Server in Mastra AI?

Instantiate the MCPClient with your secure Vinkius URL and call listTools. You can then spread these tools directly into your Mastra agent definition to give it full scraping capabilities.

Q: Can Mastra AI automatically retry failed Browse AI tasks?

Yes, you can configure Mastra workflows to poll gettask and use exponential backoff if the scraping job is still processing. If it fails, the workflow can trigger a retry automatically.

Q: How do I handle bulk scraping runs with Browse AI in Mastra AI?

Your workflow can call runbulktask to start concurrent scrapes across multiple URLs. Mastra then tracks the status with getbulktask and processes the final JSON array when complete.

Q: Can my agent check credit limits?

Yes, your agent can call listcredits to check your remaining balance. You can set up a conditional branch that pauses the workflow or alerts an admin if credits fall below a certain threshold.

Q: How secure is the scraped web data processed by Mastra AI?

All scraped JSON payloads retrieved via gettaskdata are transmitted securely through the Vinkius MCP Server directly to your Mastra deployment. We use ephemeral sandboxes to ensure your data is never cached or leaked.

Run self-healing web scraping workflows with Mastra AI and Browse AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to Mastra AI

Create your Vinkius account to connect Browse AI 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 Browse AI with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Self-Healing Scrapes with Mastra AI

Web pages change, but your automated workflows shouldn't break because of it. Use this MCP Server inside your Mastra workflows to trigger scrapers with `run_robot` and monitor their execution status automatically. If a run fails, Mastra's built-in retry logic kicks in. The workflow engine checks the status using `get_task` and can automatically try alternative URLs or notify your team if the extraction fails.

Conditional Branching for Bulk Web Extractions

Process hundreds of target pages at once by passing dynamic URL lists to `run_bulk_task`. Your Mastra agents handle the heavy lifting of preparing the URL arrays and initiating concurrent extractions. The workflow monitors the batch using `get_bulk_task`. Once finished, it conditionally branches based on the results, routing the structured JSON from `download_bulk_data` to different databases depending on the content.

Automate Site Change Responses

Let your agents keep tabs on target websites without manual intervention. By calling `list_monitors` through the MCP Server, your Mastra agent checks which active monitors are running and watches for scheduled updates. When a change is detected, the workflow can instantly trigger a new extraction task. It uses `get_task_data` to pull the fresh data and run your custom business logic.

Setup guide

Set up Browse AI 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 Browse AI 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: "browse-ai-1-mcp-client",
  servers: {
    "browse-ai-1-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

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

Instantiate the `MCPClient` with your secure Vinkius URL and call `listTools`. You can then spread these tools directly into your Mastra agent definition to give it full scraping capabilities.

Yes, you can configure Mastra workflows to poll `get_task` and use exponential backoff if the scraping job is still processing. If it fails, the workflow can trigger a retry automatically.

Your workflow can call `run_bulk_task` to start concurrent scrapes across multiple URLs. Mastra then tracks the status with `get_bulk_task` and processes the final JSON array when complete.

Yes, your agent can call `list_credits` to check your remaining balance. You can set up a conditional branch that pauses the workflow or alerts an admin if credits fall below a certain threshold.

All scraped JSON payloads retrieved via `get_task_data` are transmitted securely through the Vinkius MCP Server directly to your Mastra deployment. We use ephemeral sandboxes to ensure your data is never cached or leaked.

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