How to Use the Browserhub MCP in Mastra AI

Q: Can I require manual approval for Browserhub runs in Mastra AI?

Yes, you can set the approval flag on tools like runscraper within Mastra. This pauses the workflow and waits for human sign-off before initiating any web scraping jobs.

Q: How do Mastra AI workflows handle long Browserhub scraping jobs?

The workflow triggers runscraper and then enters a step that uses the MCP tool to poll getscrapingjob. Mastra manages this loop natively, resuming subsequent tasks only when the job is fully completed.

Q: Can my agent inspect scraper configurations dynamically?

Yes, the agent uses listscrapers and getscraper to check active configurations. This lets your agent determine which scraper is best suited for a target URL before starting a run.

Build resilient, self-healing web scraping workflows in Mastra AI using Browserhub tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserhub MCP to Mastra AI

Create your Vinkius account to connect Browserhub 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 Browserhub with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient Scraping Workflows with Mastra AI

The `run_scraper` tool integrates directly into Mastra AI workflow steps to trigger structured data extraction. If a scraping job fails due to network issues, Mastra's built-in retry engine automatically backs off and retries the job without crashing your agent. You can chain this with conditional logic to handle errors gracefully. For example, if a job fails, the agent automatically switches proxy locations and runs the scrape again, keeping your pipeline running.

Dynamic Proxy Switching in Mastra Workflows

The `list_proxy_locations` tool allows your Mastra agent to query available egress IPs before launching a scraping run. If a target site blocks your request, the agent branches the workflow to pick a new region and tries again. This programmatic control ensures high success rates for automated data gathering. Your workflows adapt to geo-blocking dynamically, using real-time proxy data rather than hardcoded endpoints.

Manage Scraping Budgets via Mastra AI MCP Server

The `get_account_balance` tool gives your Mastra workflows real-time visibility into your remaining API credits via the MCP Server. You can place a conditional step at the start of your workflow to halt execution or alert an admin if your balance drops below a specific threshold. This prevents silent failures in production when running high-volume scraping tasks. By exposing your credit balance to the agent, you build self-monitoring pipelines that manage their own operational costs.

Setup guide

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

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

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

You instantiate the MCP Server URL in your Mastra client configuration block. Mastra automatically registers all ten tools, making them instantly available to your agents and workflows.

Yes, you can set the approval flag on tools like `run_scraper` within Mastra. This pauses the workflow and waits for human sign-off before initiating any web scraping jobs.

The workflow triggers `run_scraper` and then enters a step that uses the MCP tool to poll `get_scraping_job`. Mastra manages this loop natively, resuming subsequent tasks only when the job is fully completed.

Yes, the agent uses `list_scrapers` and `get_scraper` to check active configurations. This lets your agent determine which scraper is best suited for a target URL before starting a run.

Your balance queries run through Vinkius's zero-trust gateway. Your credentials are encrypted at rest and never exposed to the agent runtime environment, ensuring your financial limits remain private.

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