How do I find my ScreenshotOne Access Key?

Log in to your [**ScreenshotOne dashboard**](https://screenshotone.com/app/settings), and you will find your Access Key under the 'API Keys' section. Copy and paste it below.

Can the agent capture elements by ID or Class?

Yes. Use the `take_element_screenshot` tool providing a valid CSS selector (e.g., `#header` or `.product-card`). Your agent will return a screenshot of just that element.

Is PDF generation supported for all sites?

Yes. The `generate_pdf` tool works for any publicly accessible URL, converting the website content into a high-quality PDF document instantly.

ScreenshotOne MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: ScreenshotOne
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ScreenshotOne through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to ScreenshotOne "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in ScreenshotOne?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About ScreenshotOne MCP Server

Empower your AI agent to orchestrate your entire visual auditing and website capturing workflow with ScreenshotOne, the reliable API for high-quality screenshots. By connecting ScreenshotOne to your agent, you transform complex capturing tasks into a natural conversation. Your agent can instantly take full-page screenshots, generate PDFs from URLs, and audit page metadata without you ever touching a browser. Whether you are monitoring site changes or archiving visual content, your agent acts as a real-time visual archiver, ensuring your records are always clear and comprehensive.

Pydantic AI validates every ScreenshotOne tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Visual Auditing — Take high-resolution screenshots of any URL and retrieve the direct image links instantly.
Full-page Oversight — Capture entire website pages from top to bottom to maintain a complete view of site design and content.
Document Intelligence — Generate professional PDFs from any website for easy sharing and offline auditing.
Metadata Discovery — Retrieve website titles, descriptions, and page sizes without performing a full capture.
Targeted Capturing — Take screenshots of specific CSS elements or custom viewports to focus on what matters most.

The ScreenshotOne MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect ScreenshotOne to Pydantic AI via MCP

Follow these steps to integrate the ScreenshotOne MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from ScreenshotOne with type-safe schemas

Why Use Pydantic AI with the ScreenshotOne MCP Server

Pydantic AI provides unique advantages when paired with ScreenshotOne through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your ScreenshotOne integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your ScreenshotOne connection logic from agent behavior for testable, maintainable code

ScreenshotOne + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the ScreenshotOne MCP Server delivers measurable value.

Type-safe data pipelines: query ScreenshotOne with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple ScreenshotOne tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query ScreenshotOne and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock ScreenshotOne responses and write comprehensive agent tests

ScreenshotOne MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect ScreenshotOne to Pydantic AI via MCP:

generate_pdf

Generate a PDF from a URL

get_page_metadata

) without capturing. Get metadata for a website (title, size, etc.) without capturing

take_element_screenshot

Take a screenshot of a specific CSS element

take_full_page_screenshot

Take a full-page screenshot of a URL

take_screenshot

Take a screenshot of a URL

take_viewport_screenshot

Take a screenshot with a specific viewport size

Example Prompts for ScreenshotOne in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with ScreenshotOne immediately.

"Take a screenshot of https://vinkius.com."

"Capture the full page of https://github.com/vinkius."

"Show metadata for https://www.google.com."

Troubleshooting ScreenshotOne MCP Server with Pydantic AI

Common issues when connecting ScreenshotOne to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ScreenshotOne + Pydantic AI FAQ

Common questions about integrating ScreenshotOne MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your ScreenshotOne MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.