How to Use the SEON MCP in Pydantic AI

Q: If we need to manage security rules using SEON and Pydantic AI, how do we proceed?

You can use listrules to retrieve the current state of fraud parameters. Since the output is typed, your agent can read these rules and then generate clean code or configuration updates based on them.

Q: Can SEON help us with AML requirements using Pydantic AI?

Yes. The amlscreening tool provides compliance results that are automatically typed. This means your agent can confidently pass the results—whether they are clean or flagged—to audit logs.

Q: What data types does the SEON MCP Server touch regarding privacy?

The server handles structured data points: IP addresses (checkip), email footprints (checkemail), and phone numbers (checkphone). All these inputs are received by your agent as strongly typed objects.

Ensure data correctness: Get validated fraud intelligence with Pydantic AI and SEON MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect SEON MCP to Pydantic AI

Create your Vinkius account to connect SEON 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 SEON with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate transaction risk scores precisely.

When you run `check_fraud`, the response is guaranteed to match a Pydantic model. You won't get unexpected fields or missing data, which stops silent corruption in your agent logic. Use `get_transaction` and validate its output immediately. This ensures that every piece of raw data—like timestamps or amounts—is structured exactly how you expect it.

Maintain type-safe identity checks.

Need to check a phone number? Calling `check_phone` returns a validated object, not just a string. This is crucial because your agent relies on the data type being correct for downstream logic. Similarly, using `get_account_info` means you'll always receive structured fields like account IDs and creation dates, eliminating guesswork.

Structure compliance checks reliably.

When running an `aml_screening`, the output structure is predictable. This predictability lets your agent confidently pass the results to other internal systems without needing extra validation layers. For managing lists, tools like `list_rules` provide a clean, defined schema for all current fraud policies.

Setup guide

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

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

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

The core benefit is that every single response from the MCP Server validates against a strict schema. If `check_fraud` returns malformed JSON, your agent fails loud and clear—no bad data gets processed.

SEON gives you real-time risk scores by checking multiple factors: device fingerprints, IP address risks (`check_ip`), and behavioral anomalies. This is all packaged into a structured result your agent trusts.

You can use `list_rules` to retrieve the current state of fraud parameters. Since the output is typed, your agent can read these rules and then generate clean code or configuration updates based on them.

Yes. The `aml_screening` tool provides compliance results that are automatically typed. This means your agent can confidently pass the results—whether they are clean or flagged—to audit logs.

The server handles structured data points: IP addresses (`check_ip`), email footprints (`check_email`), and phone numbers (`check_phone`). All these inputs are received by your agent as strongly typed objects.

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