How to Use the Urlbox MCP in Pydantic AI

Q: Can I use Urlbox for mobile view testing with Pydantic AI?

Yes, you can call takemobilescreenshot. Your agent processes this tool’s output, and because of Pydantic's validation, it guarantees that the resulting image data is correctly formatted before your code even sees it.

Guaranteed data structures for web assets using Pydantic AI validation with the MCP Server.

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 Pydantic AI

Create your Vinkius account to connect Urlbox to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structured Screenshot Capture

When capturing images, you need predictable outputs. Use `take_screenshot` to get a standard PNG, but know that your agent's goal is always type safety. The MCP Server ensures the resulting asset can be treated as a confirmed binary object within your Pydantic model.

Metadata with Type Validation

The `get_metadata` tool extracts web data, but crucially, it provides fields that match defined types. Instead of getting a dictionary of strings, you get structured keys (like title or description) that fit your Pydantic model perfectly, avoiding runtime errors.

Validated PDF Generation

Generating PDFs is fine, but the output needs to be trustworthy. Use `generate_pdf` knowing that while the content is rendered from a URL, the resulting artifact can be processed through your agent's validation logic for downstream reliability.

Setup guide

Set up Urlbox MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "urlbox-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Urlbox tools.",
)

result = await agent.run("List recent Urlbox transactions")
print(result.output)

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 Pydantic AI

The MCP Server exposes its tools to your Agent, but the real power is in the output. Every time an agent calls a tool like `take_full_page_screenshot`, the resulting data must conform to the schema you defined in Pydantic.

Yes, you can call `take_mobile_screenshot`. Your agent processes this tool’s output, and because of Pydantic's validation, it guarantees that the resulting image data is correctly formatted before your code even sees it.

It touches visual content (screenshots and PDFs) and source text metadata. The key benefit here is that the *schema* of these outputs—the structure itself—is what you are validating, making your whole system robust.

You can. The tool provides source metadata that adheres to a defined structure. This means you don't have to write custom parsing logic; your agent just reads the confirmed fields.

It is dependable. While the tool creates a PDF from a URL, your downstream process can validate that specific metadata points (like page count or file size) derived from the MCP Server's output conform to expected types.

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