How to Use the Urlbox MCP in Pydantic AI

Q: How do I ensure the output from Urlbox is correct using Pydantic AI?

The capturepdf tool provides data that must conform to your defined models. If the underlying API returns unexpected fields, Pydantic AI catches it immediately, preventing corrupted data from entering your system.

Q: What is the best practice for rendering large sites with Urlbox and Pydantic AI?

Use renderasync to initiate the job. Then, use getrenderstatus in a loop until confirmation. This structured polling method fits perfectly into your type-safe execution flow.

Q: Can Pydantic AI validate the list of webhooks from Urlbox?

Yes, calling listwebhooks gives you a list that can be passed through validation. This ensures that any subsequent calls to trigger or manage those webhooks use properly structured parameters.

Q: If I need proxy data, how do I handle it with Urlbox and Pydantic AI?

The agent calls listproxies first. The resulting list of proxies is then validated against your schema, ensuring every IP address or range adheres to the expected format before use.

Get verifiable web captures and rendering results using Pydantic AI's type safety.

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

Type-Safe Web Capture with MCP Server

The `capture_pdf` tool converts URLs into structured PDF outputs. Similarly, the `capture_png` function provides verifiable image data for your agent to work with. Since Pydantic AI demands correctness, this ensures the captured output always conforms to expected types. This process prevents silent corruption; if the capture fails or returns malformed data, your agent fails loudly with a validation error.

Validate Storage and Proxy Listings

Before rendering, agents must verify resources. The `list_storage_buckets` tool provides a list of storage locations, which the agent then validates against its schema. They can also check network availability by calling `list_proxies`. This strict validation process guarantees data integrity. It's all about making sure the input parameters for rendering are correct before execution.

Check Status and Account Info with Pydantic AI

The agent uses `get_render_status` to verify a job's completion state, ensuring it doesn't try to process incomplete data. It also calls `get_account_info` to validate the current profile details before starting any resource-intensive task. This pattern of pre-validation is exactly why Pydantic AI works so well with critical backend services like this MCP Server.

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-alternative-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 `capture_pdf` tool provides data that must conform to your defined models. If the underlying API returns unexpected fields, Pydantic AI catches it immediately, preventing corrupted data from entering your system.

Use `render_async` to initiate the job. Then, use `get_render_status` in a loop until confirmation. This structured polling method fits perfectly into your type-safe execution flow.

Yes, calling `list_webhooks` gives you a list that can be passed through validation. This ensures that any subsequent calls to trigger or manage those webhooks use properly structured parameters.

The agent calls `list_proxies` first. The resulting list of proxies is then validated against your schema, ensuring every IP address or range adheres to the expected format before use.

The server accesses usage statistics and basic account profile details when you call `get_account_info`. This access is always treated as structured data, allowing your agent to validate the returned JSON fields.

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