How to Use the autoRetouch MCP in Pydantic AI

Q: How do I register the autoRetouch MCP Server with my Pydantic AI agent?

Install the package with pip install "pydantic-ai-slimmcp". Use the MCPToolset class to connect to the server URL, and pass that toolset directly into the Agent's toolsets list.

Q: Does autoRetouch support runtime validation in Pydantic AI?

Yes, every tool response from getimage to listworkflows is validated against Pydantic schemas. If the server response drifts or changes, the framework raises a validation error immediately rather than letting your agent hallucinate.

Ensure zero-drift, type-safe image processing workflows by combining autoRetouch with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect autoRetouch MCP to Pydantic AI

Create your Vinkius account to connect autoRetouch 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 autoRetouch with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run type-safe edits with Pydantic AI

Stop worrying about API schema changes breaking your production image pipeline. When your agent calls `create_execution` or `list_workflows`, every single field is validated against strict Pydantic models at runtime. If the API returns an unexpected data type, the agent raises a clear validation error immediately. This strict validation prevents corrupt image metadata from polluting your database. You can safely run complex background removals knowing that your agent will never write malformed URLs or invalid execution IDs to your catalog.

Validate e-commerce batch states via MCP Server

Monitoring large-scale photo edits requires absolute precision. Your agent uses `get_batch` and `list_batches` to track the state of your active editing queues. Because the responses are strictly typed, your agent can reliably parse progress percentages and file counts without risking silent parsing failures. If a batch fails, the agent reads the exact error payload from `get_execution`. The typed models ensure your error-handling logic receives clean, predictable strings, allowing your system to automatically trigger retries or alert developers.

Track operational balances with zero schema drift

Keep your automated studio from running dry. The agent calls `get_wallet_balance` to check your remaining credits before initiating new bulk runs. By validating the balance payload against strict numeric types, your agent can make accurate logical decisions about whether to proceed. This type-safe check prevents casting errors that could cause your agent to misinterpret your balance. You get a reliable guardrail that keeps your production pipeline running smoothly across any LLM you choose to plug in.

Setup guide

Set up autoRetouch 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": {
        "autoretouch-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent autoRetouch 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 autoRetouch. 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 autoRetouch 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 autoRetouch MCP in Pydantic AI

Install the package with pip install "pydantic-ai-slim[mcp]". Use the MCPToolset class to connect to the server URL, and pass that toolset directly into the Agent's toolsets list.

Yes, every tool response from get_image to list_workflows is validated against Pydantic schemas. If the server response drifts or changes, the framework raises a validation error immediately rather than letting your agent hallucinate.

The MCP Server catches the schema mismatch or API error and raises a clear validation exception. This lets you handle failures gracefully in your Python code instead of dealing with silent failures or corrupt catalog data.

Yes, Pydantic AI is model-agnostic. You can connect this toolset to local models or alternative APIs, and the runtime validation will still guarantee that the model uses the tools like list_images correctly.

All communication with the server goes through secure, ephemeral transport layers. Your product photos are processed in isolated sandboxes, and their raw pixel data is never cached or used to train any underlying language models.

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