How to Use the Adyen MCP in Pydantic AI

Q: How do I load this Adyen MCP Server into Pydantic AI?

Install pydantic-ai-slimmcp and instantiate MCPToolset with your Vinkius Adyen HTTP endpoint. Pass this toolset into your Pydantic AI Agent constructor using the toolsets parameter.

Q: Does Pydantic AI support SSE transport for this Adyen MCP Server?

Yes, the unified MCPToolset class in Pydantic AI supports both Streamable HTTP and SSE transports to communicate with your externally running Adyen server. These transports let you choose the best connection mechanism for your stack.

Build type-safe payment workflows in Pydantic AI with runtime validation for Adyen transactions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adyen MCP to Pydantic AI

Create your Vinkius account to connect Adyen 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 Adyen with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe refund execution with Pydantic AI

Moving money in Adyen requires your Pydantic AI agent to invoke `refund_payment` with absolute certainty that your data structures are correct. When your Pydantic AI agent triggers this tool, the framework validates the 16-digit PSP reference and refund amount against strict schemas before the request ever leaves your system. If the Pydantic AI agent tries to send an invalid PSP format or a non-numeric refund amount, the runtime raises a validation error immediately. This prevents malformed Adyen requests from corrupting your financial logs or failing silently at the API level.

Validated merchant discovery via Pydantic AI

Discovering active Adyen merchant accounts requires your Pydantic AI agent to run `list_merchants` to pull active profiles from global regions. Using this MCP Server, your agent calls the tool to find active profiles, parsing the raw response into structured Pydantic models. Once validated, your Pydantic AI agent can safely call `get_merchant_details` to inspect the technical configurations of specific accounts. Any missing or malformed configuration fields will cause your Pydantic AI agent to fail loudly, ensuring you only process clean Adyen data.

Strict payment metadata parsing

Parsing Adyen authorization and capture metadata is handled when your Pydantic AI agent executes `get_payment_details` to fetch metadata for specific transactions. This tool delivers detailed transaction states that are instantly bound to your type-safe Python models. This guarantees that your downstream business logic receives exactly the Adyen data types it expects inside Pydantic AI. By passing the MCP Server toolset to your agent, you integrate these strict validation layers with any supported LLM provider in Pydantic AI.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and instantiate `MCPToolset` with your Vinkius Adyen HTTP endpoint. Pass this toolset into your Pydantic AI `Agent` constructor using the `toolsets` parameter.

The Pydantic AI framework will raise a validation error at runtime, stopping the agent from processing corrupted Adyen data. Catching these errors early prevents bad API payloads from reaching your backend.

Yes, the unified `MCPToolset` class in Pydantic AI supports both Streamable HTTP and SSE transports to communicate with your externally running Adyen server. These transports let you choose the best connection mechanism for your stack.

Yes, Pydantic AI is model-agnostic, allowing you to pair these validated Adyen tools with local models while maintaining strict runtime checks. Running locally ensures your transaction schema remains private.

All Adyen merchant IDs and payment details are processed in memory and validated locally by your Pydantic AI schemas. Vinkius handles the MCP connection using zero-trust, ephemeral environments that never store your Adyen API credentials or transaction logs.

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