How to Use the SEON MCP in Vercel AI SDK

Q: How does SEON help with real-time fraud checks in ai-sdk?

It streams results instantly. Your AI client calls checkfraud, and instead of waiting for a single payload, the data appears in your UI piece by piece. This makes the process feel immediate to the end user.

Q: Can I use SEON's AML screening tool with ai-sdk?

Yes. You can invoke amlscreening through the MCP Server and display the results immediately in your application. This is useful for compliance checks during user sign-up.

Q: Is the SEON MCP Server suitable for Next.js frontends?

Absolutely. The ai-sdk is designed specifically for building user-facing products where streaming data directly into React, Next.js, or Svelte components works flawlessly.

Q: Does SEON support complex transaction history lookups with ai-sdk?

Yes. You can pull detailed records using gettransaction to populate a user's activity feed. The data streams out, letting your front-end render the full timeline quickly.

Stream real-time risk scores directly into your Next.js UI with SEON and ai-sdk.

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 Vercel AI SDK

Create your Vinkius account to connect SEON to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Fraud Scoring via MCP Server

When a user submits credentials, you can instantly check the associated IP risk data using `check_ip` or perform a full identity scan with `check_fraud`. The results stream right into your React component, showing the final score without ever hitting a loading spinner. This immediate feedback loop makes for a smooth user experience. Your agent calls the SEON MCP Server, and you display the data as it comes back—perfect for building frontends where speed matters.

Identity Validation Tools in ai-sdk

You don't have to make separate API calls just to validate basic identity fields. Use tools like `check_email` or `check_phone` inside your workflow. This lets you gather a complete digital footprint before proceeding with the transaction. It's great for user onboarding because you can present the validation status (e.g., 'Email verified,' 'Phone clean') right next to the input fields as data streams in.

Managing Fraud Rules and Lists

Your front-end logic needs to respect established security boundaries. Use `list_rules` to see all existing fraud rules, or use `add_to_list` via the MCP Server to immediately blacklist a user's IP address. This keeps your client side compliant with backend policies. You can also read and write to custom lists using `list_lists`, making it easy for your agent to manage whitelists and blacklists directly from the UI layer.

Setup guide

Set up SEON MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all SEON tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent SEON transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

It streams results instantly. Your AI client calls `check_fraud`, and instead of waiting for a single payload, the data appears in your UI piece by piece. This makes the process feel immediate to the end user.

Yes. You can invoke `aml_screening` through the MCP Server and display the results immediately in your application. This is useful for compliance checks during user sign-up.

It primarily handles identifiers like email addresses, phone numbers, and IP risk data when running tools such as `check_email` or `get_transaction`. Always remember to respect user consent.

Absolutely. The `ai-sdk` is designed specifically for building user-facing products where streaming data directly into React, Next.js, or Svelte components works flawlessly.

Yes. You can pull detailed records using `get_transaction` to populate a user's activity feed. The data streams out, letting your front-end render the full timeline quickly.

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