How to Use the Effiliation MCP in Vercel AI SDK

Q: How do I initialize the Effiliation MCP Server in Vercel AI SDK?

Install the packages via npm install ai @ai-sdk/mcp. Use createMCPClient to point to your Vinkius endpoint, then pass the tools directly into your generateText or streamText calls.

Q: Can I stream live commission updates using Effiliation and Vercel AI SDK?

Yes, the streaming nature of this client ensures that when getperformancestatistics runs, the metrics stream directly to the user interface. This avoids the lag associated with traditional REST polling.

Q: How does Vercel AI SDK handle connection pooling with the Effiliation MCP Server?

You must call mcpClient.close() once your streaming session finishes. This prevents orphaned connections on your serverless endpoints when pulling transaction data through listaffiliatetransactions.

Q: How do I handle user-specific authentication for the API?

Configure the authProvider option within the SDK client setup. This allows you to securely pass user-specific tokens to isolate their geteffiliationmetadata queries.

Stream real-time affiliate earnings and campaign metrics directly into your Next.js frontend with Vercel 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 Effiliation MCP to Vercel AI SDK

Create your Vinkius account to connect Effiliation 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 Effiliation with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time audit dashboards in Vercel AI SDK

Stop waiting for cron jobs to tell you if your affiliate revenue is leaking — and this is where it leaks — when tracking pixels fail. Your React frontend can now query the Effiliation API live using `quick_affiliate_revenue_audit` to display instant commission health scores. Because this MCP client streams tool outputs directly, users see live payout numbers populate their UI without staring at blank loading spinners. Feed the raw transaction streams straight to your UI components. By calling `list_latest_conversions` within your Edge Functions, the client renders live sales data as it ticks. You get zero-latency visibility into campaign performance without writing custom API polling logic.

Instant program search for active frontends

Let your users hunt down profitable partnerships inside your chat interface. The client takes the tool array from `mcpClient.tools()` and hands it to `streamText`, letting your UI instantly display program details. The AI agent triggers `search_affiliate_programs` and `get_program_details` on demand. It pulls commission structures and terms directly into the active chat session, letting users evaluate deals on the fly.

Stream live financial audits to the Edge

Reconcile historical payout discrepancies without leaving your Web Vitals-optimized app. This MCP Server exposes `list_account_payments` to verify every bank settlement against your records. Running this on Edge Functions means your application handles heavy affiliate audits without hitting cold starts. Close the loop by calling `mcpClient.close()` to keep your serverless execution clean and fast.

Setup guide

Set up Effiliation 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 Effiliation 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 Effiliation 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 Effiliation. 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 Effiliation 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 Effiliation MCP in Vercel AI SDK

Install the packages via `npm install ai @ai-sdk/mcp`. Use `createMCPClient` to point to your Vinkius endpoint, then pass the tools directly into your `generateText` or `streamText` calls.

Yes, the streaming nature of this client ensures that when `get_performance_statistics` runs, the metrics stream directly to the user interface. This avoids the lag associated with traditional REST polling.

You must call `mcpClient.close()` once your streaming session finishes. This prevents orphaned connections on your serverless endpoints when pulling transaction data through `list_affiliate_transactions`.

Configure the `authProvider` option within the SDK client setup. This allows you to securely pass user-specific tokens to isolate their `get_effiliation_metadata` queries.

Your raw transaction logs, commission rates, and payout histories fetched by `list_affiliate_transactions` run through V8 sandbox isolates. No affiliate data is stored on Vinkius; it goes directly from the API to your client.

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