How to Use the Skalin MCP in Vercel AI SDK

Q: How do I integrate Skalin data with Vercel AI SDK?

You initialize the connection using createMCPClient() and call mcpClient.tools(). Your agent then uses these tools to fetch specific Skalin data, which you receive as a stream directly into your Next.js or Svelte component.

Q: Does the Skalin MCP Server support real-time logging for Vercel AI SDK?

Yes, absolutely. When you call loginteraction, the data streams back to your client instantly. This makes it perfect for building dashboards where activity needs to appear live as the agent processes it.

Q: If I use Vercel AI SDK, how do I handle multiple agent roles for Skalin?

You pass the full set of available tools to generateText or streamText. Your agent determines which tool is needed—whether it's checking alerts with listcsalerts or updating tasks with updatecstask.

Real-time customer health insights from Skalin, streamed live to your UI with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Skalin MCP to Vercel AI SDK

Create your Vinkius account to connect Skalin to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Skalin with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check Live Account Status via MCP Server

The `get_account_health` tool instantly checks a client's current status. You stream this data into your UI, allowing users to see health scores update live without refreshing the page. Need more info? Use `list_cs_alerts` for active issues or `get_api_status` to confirm connectivity details. Your agent handles all these calls and streams the results back immediately.

Log Interactions and View History

Need to record a meeting? Call `log_interaction` and send the data stream directly into your application's activity log. This lets users see who talked to whom, right when it happens. To review past activity, use `list_account_interactions`. It pulls all account history records so you can display them in real-time components.

Manage Tasks and Contacts

The `list_cs_tasks` tool lets your agent pull a list of success tasks. You'll stream this array to the UI, letting users immediately see what needs fixing or following up on. You can also use `update_cs_task` to modify task details and `list_account_contacts` to grab the latest contact information for the account.

Setup guide

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

You initialize the connection using `createMCPClient()` and call `mcpClient.tools()`. Your agent then uses these tools to fetch specific Skalin data, which you receive as a stream directly into your Next.js or Svelte component.

The MCP Server manages several account views. You can list all customer accounts using `list_cs_accounts`, check an individual's health with `get_account_health`, or grab usage metrics via `get_account_metrics`.

Yes, absolutely. When you call `log_interaction`, the data streams back to your client instantly. This makes it perfect for building dashboards where activity needs to appear live as the agent processes it.

This MCP Server touches sensitive account health and usage data. All calls are managed through a secure, single endpoint token, keeping your application isolated from the underlying system.

You pass the full set of available tools to `generateText` or `streamText`. Your agent determines which tool is needed—whether it's checking alerts with `list_cs_alerts` or updating tasks with `update_cs_task`.

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