How to Use the Blueshift MCP in Vercel AI SDK

Q: How do I connect Blueshift to Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient with your Vinkius HTTP endpoint. Pass the tools directly to streamText and make sure to call mcpClient.close() when the request finishes.

Q: Does Vercel AI SDK support Blueshift user authentication?

Yes, you can use the SDK's authProvider to handle OAuth tokens. This ensures each user only accesses their own marketing data when calling tools like getcustomer.

Stream real-time Blueshift campaign metrics and customer profile updates directly into your Next.js UI using the 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 Blueshift MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Blueshift Campaign Data with Vercel AI SDK

The `get_campaign_performance` and `get_campaign_detail` tools pull marketing analytics directly into your application's frontend. Your AI client invokes these tools to fetch raw performance metrics and format them on the fly. Because we use this Vercel AI SDK setup, the data renders in your UI as it arrives instead of making users wait for a slow API handshake to finish. You don't need to build custom loading screens or backend polling routes. Connect the server using `createMCPClient` and pass the tools directly to `streamText`. Your users watch the AI pull live open rates and click counts into the dashboard in real-time.

Update Customer Profiles on the Edge

The `create_update_customer` tool writes user attributes directly to your marketing database from Edge Functions. This setup allows your AI client to modify profiles instantly based on user chat behavior. You handle identity updates right at the network edge, dropping latency down to single-digit milliseconds. To make this work, fetch the customer data via `get_customer` first to see what needs changing. The Vercel AI SDK handles the MCP tool execution loop, allowing your model to decide which fields to update and execute the write operation without spinning up heavy Node.js runtimes.

Pull Live Product Catalogs Into Chat

The `get_catalog_items` and `list_catalogs` tools let your conversational agent browse through your active Blueshift inventory. Your AI client reads these catalogs to suggest relevant products to users during a support session. By feeding these tools into your model, you turn a basic chat interface into an interactive shopping assistant. Simply map the tools from your MCP Server instance into the `generateText` function. The SDK handles the schema validation, so your model receives structured catalog items and presents them to the user without formatting errors.

Setup guide

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

Install `@ai-sdk/mcp` and use `createMCPClient` with your Vinkius HTTP endpoint. Pass the tools directly to `streamText` and make sure to call `mcpClient.close()` when the request finishes.

Yes, this server is fully compatible with Edge runtimes. Since Vinkius hosts the server, your Next.js Edge Functions only need to make lightweight HTTP requests to our secure endpoint.

The SDK streams tool calls and results block-by-block directly to the client. This means your UI updates progressively as `get_campaign_performance` or `get_event_history` returns data.

Yes, you can use the SDK's `authProvider` to handle OAuth tokens. This ensures each user only accesses their own marketing data when calling tools like `get_customer`.

We secure your customer profiles, campaign logs, and event histories using V8 isolate sandboxes on Vinkius. Your API credentials never touch the client browser, and all data transfers run over encrypted TLS channels with zero persistent storage.

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