How to Use the AirOps MCP in Vercel AI SDK

Q: How do I run an AirOps workflow with the Vercel AI SDK?

You call executeworkflowsync for quick jobs or executeworkflowasync for longer ones. Pass the tool results from the MCP client directly into the generateText or streamText function. The SDK handles streaming the output.

Q: Can my Vercel AI SDK app check the status of an AirOps job?

Yes, that's what getexecutionstatus is for. You give it the execution ID from an async call, and it returns the current progress. It's perfect for showing live updates in your UI.

Q: Is it possible to search an AirOps memory store using the Vercel AI SDK?

Yes. The searchmemorystore tool lets your agent query the vector database. Since you're using the AI SDK, the search results can stream directly into your UI components as they are found.

Q: What's the best way to get started?

Install the packages, then use createMCPClient with your Vinkius endpoint URL. You can get the available tools by calling mcpClient.tools() and pass them to your AI model. Remember to call mcpClient.close() to terminate the connection.

Build UIs that react in real-time. Connect the Vercel AI SDK to AirOps to stream workflow results directly into your frontend components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirOps MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run & Monitor Workflows from the UI

Let your users kick off complex AI jobs without leaving your app. The `execute_workflow_async` tool starts a process on AirOps, and `get_execution_status` lets you build a live progress bar right in your UI. If a user changes their mind, `cancel_execution` stops the job instantly. All of this streams back through the Vercel AI SDK. That means your interface updates as the status changes, with no page reloads or polling. It just feels fast.

Give Your AI SDK App a Memory

This MCP Server connects your frontend to a persistent knowledge base. Use `upload_file` to let users add their own data, then `add_memory_document` to index it. Now your AI has context that lasts beyond a single session. When it's time to find that information again, `search_memory_store` queries the vector database. The results stream back, so you can build a search interface that shows answers as they're found.

Manage AirOps Apps Directly

Your UI can become a control panel for AirOps itself. The `list_apps` tool gets all available AI applications, and `get_app_details` pulls the specific metadata for each one. You can build a dynamic dashboard for your users. Pair this with `chat_with_agent` to create a direct line of communication. Your users can interact with specialized AirOps agents, all managed through your Vercel-powered frontend.

Setup guide

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

You call `execute_workflow_sync` for quick jobs or `execute_workflow_async` for longer ones. Pass the tool results from the MCP client directly into the `generateText` or `streamText` function. The SDK handles streaming the output.

Yes, that's what `get_execution_status` is for. You give it the execution ID from an async call, and it returns the current progress. It's perfect for showing live updates in your UI.

Yes. The `search_memory_store` tool lets your agent query the vector database. Since you're using the AI SDK, the search results can stream directly into your UI components as they are found.

Install the packages, then use `createMCPClient` with your Vinkius endpoint URL. You can get the available tools by calling `mcpClient.tools()` and pass them to your AI model. Remember to call `mcpClient.close()` to terminate the connection.

The server primarily handles execution data, like workflow IDs and status updates. When you use tools like `upload_file` or `add_memory_document`, it processes the file content and document text you provide. Your Vinkius endpoint is sandboxed and ephemeral, so compute sessions are isolated.

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