How to Use the Mirakl (Enterprise Marketplace Platform) MCP in Pydantic AI

Q: How do I register the Mirakl (Enterprise Marketplace Platform) MCP Server in Pydantic AI?

Install the package with pip install "pydantic-ai-slimmcp" and instantiate MCPToolset with your HTTP endpoint. Pass this toolset directly into the toolsets parameter of your Pydantic AI Agent constructor to start using the validated Mirakl tools.

Q: How does Pydantic AI guarantee the privacy of my Mirakl (Enterprise Marketplace Platform) seller shop data?

All shop details pulled via getshop are processed in memory and validated locally on your server. Vinkius runs the MCP Server in an isolated V8 sandbox with single-token authentication, meaning your third-party Mirakl merchant configurations remain entirely private within your Pydantic AI environment.

Build type-safe Pydantic AI agents with this MCP Server to validate Mirakl seller configurations and orders at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mirakl (Enterprise Marketplace Platform) MCP to Pydantic AI

Create your Vinkius account to connect Mirakl (Enterprise Marketplace Platform) 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 Mirakl (Enterprise Marketplace Platform) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Order Tracking with Pydantic AI

Stop worrying about your agent acting on corrupted or malformed transaction data. This MCP Server forces all outputs from `get_order` and `list_orders` to pass strict runtime validation before your Pydantic AI code ever sees them. If a third-party Mirakl seller sends an unexpected data type, Pydantic AI fails loudly and instantly. This prevents silent database corruption and ensures your multi-vendor checkout tracking remains completely reliable.

Validated Seller Shop Diagnostics

Auditing third-party merchant accounts requires absolute accuracy. By using this toolset, your Pydantic AI agent calls `list_shops` and `get_shop` to pull deep configuration schemas that are validated against native Python models. You get complete peace of mind knowing that each Mirakl shop status, seller limit, and configuration parameter matches your exact Pydantic schema. If a merchant's profile deviates, the Pydantic AI agent catches the error before triggering downstream workflows.

Structured Inventory and Category Parsing

Managing complex marketplace hierarchies is prone to formatting bugs. This integration lets your Pydantic AI agent fetch structural category trees and live inventory details using `list_categories` and `list_offers` from Mirakl. Because each response is parsed into clean Pydantic models, your agent can safely map products to precise category nodes on Mirakl. This eliminates the risk of hallucinated fields or broken pricing arrays in your catalog.

Setup guide

Set up Mirakl (Enterprise Marketplace Platform) 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": {
        "mirakl-enterprise-marketplace-platform-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mirakl (Enterprise Marketplace Platform) 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 Mirakl. 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 Mirakl (Enterprise Marketplace Platform) 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 Mirakl (Enterprise Marketplace Platform) MCP in Pydantic AI

Install the package with `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your HTTP endpoint. Pass this toolset directly into the `toolsets` parameter of your Pydantic AI `Agent` constructor to start using the validated Mirakl tools.

The Pydantic AI agent will raise a validation error immediately rather than processing bad data. This loud-failure model ensures your code never processes malformed data from tools like `list_invoices` or `get_offer` on Mirakl.

Yes, you can connect the Mirakl server using either Streamable HTTP or SSE transports. This lets your Pydantic AI agent continuously monitor live marketplace activity like `list_messages` with minimal latency.

Absolutely, Pydantic AI is completely model-agnostic and validates all incoming schemas. You can use the same marketplace tools, like `list_products`, whether your Pydantic AI agent is powered by a local model or a commercial API.

All shop details pulled via `get_shop` are processed in memory and validated locally on your server. Vinkius runs the MCP Server in an isolated V8 sandbox with single-token authentication, meaning your third-party Mirakl merchant configurations remain entirely private within your Pydantic AI environment.

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