How to Use the Urlbox MCP in Mastra AI

Q: Can I check rendering status with Urlbox using Mastra AI?

Yes, you'll call getrenderstatus. This is perfect for your multi-step workflows because it allows one step to wait reliably for the result of another async operation.

Q: Does Urlbox support multiple types of web rendering with Mastra AI?

It does. You can use renderhtml for raw code or renderselector for specific elements, letting your workflow choose the best method based on the failure point.

Build reliable, multi-step workflows with Mastra AI and Urlbox.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Urlbox MCP to Mastra AI

Create your Vinkius account to connect Urlbox 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 Urlbox with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Capture web data for workflow steps.

The `capture_pdf` tool lets your workflow get a PDF of any URL. If the first step fails, your second step can retry by capturing another screenshot using `capture_png`. This makes the whole process robust. You're building complex operations here. After gathering data, you might need to check usage stats with `get_credit_usage` before notifying an admin. Mastra AI handles that conditional logic for you.

Manage asynchronous web content rendering.

When a job takes time, don't let your workflow hang. Use `render_async`. The result gets sent to a webhook endpoint, and the workflow waits on that signal rather than timing out. This is critical for reliable multi-step processes. Need to ensure the data source is good? You can list available proxies using `list_proxies` at the start of your flow. It guarantees the rendering step uses clean, working endpoints.

Get and manage site configuration details.

Before executing a major action, check what's available. Use `get_account_info` to validate credentials or `list_storage_buckets` to confirm where the output data needs to go. These are great initial checks in a workflow. If your flow involves specific sections of a website, you can target them using `render_selector`. This makes sure the subsequent steps only process the exact information needed.

Setup guide

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

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

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

Mastra AI handles automatic retries for failed tool calls. If `capture_png` fails due to a timeout, the framework can automatically retry using exponential backoff, making your workflow reliable.

The server provides various types of web content: PDF files from `capture_pdf`, images from `capture_png`, and structured text from selectors. Your workflow handles the conditional use of this data.

Yes, you'll call `get_render_status`. This is perfect for your multi-step workflows because it allows one step to wait reliably for the result of another async operation.

It does. You can use `render_html` for raw code or `render_selector` for specific elements, letting your workflow choose the best method based on the failure point.

The primary data types involved are URL content (text/images) and account profile information. Always ensure your workflow adheres to data residency rules when processing this sensitive web data.

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