How to Use the Argo Workflows MCP in Vercel AI SDK

Q: How do I connect Argo Workflows to my Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using createMCPClient with the Vercel endpoint. Pass the tools directly into streamText or generateText so your agent can call listworkflows on demand. Always call mcpClient.close() to clean up active connections in your serverless functions.

Stream live Kubernetes execution states directly to your Next.js frontend using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Argo Workflows MCP to Vercel AI SDK

Create your Vinkius account to connect Argo Workflows 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 Argo Workflows with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream active workflow steps to React components

Stop making users stare at loading spinners while Kubernetes runs heavy jobs. This Vercel AI SDK integration lets your frontend stream live step-by-step progress as it happens in your cluster. By calling `get_workflow` inside your Edge Functions, your app fetches the exact JSON resource tree and pushes it down to the client. The UI updates instantly with active pod statuses, run durations, and failure nodes. You write the UI layer, and the SDK handles the real-time pipeline without custom WebSockets or polling loops.

Query history directly from Vercel AI SDK edge functions

Fetching old pipeline runs shouldn't require a slow backend proxy. This MCP Server lets your agent pull historical records instantly using `list_archived_workflows` directly from the edge. Your application can dynamically generate post-mortem reports or audit trails on demand. Since the edge runtime handles the connection, users get their data in milliseconds instead of waiting for heavy database queries.

Manage cron schedules with the Vercel AI SDK

Let users inspect or modify scheduled jobs right inside your chat interface. By exposing `list_cron_workflows` to the AI client, your application lists active schedules and helps developers spot overlaps or misconfigured intervals. The agent reads the exact cron specs and translates them into readable tables on the fly. It gives your team instant visibility into cluster automation without leaving the browser tab.

Setup guide

Set up Argo Workflows 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 Argo Workflows 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 Argo Workflows 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 Argo Workflows. 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 Argo Workflows 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 Argo Workflows MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient` with the Vercel endpoint. Pass the tools directly into `streamText` or `generateText` so your agent can call `list_workflows` on demand. Always call `mcpClient.close()` to clean up active connections in your serverless functions.

Yes, the SDK streams the tool outputs as they arrive from the cluster. By using `get_workflow`, your agent receives the live status of individual pods and streams those updates directly into your React components. This eliminates the need for manual polling or setting up custom state managers.

You can distribute different tools to specialized agents within your TS codebase. For example, give a monitoring agent access to `list_workflows` while keeping template modification restricted. This keeps your edge functions lightweight and highly secure.

Vinkius handles the underlying credentials so your code stays clean. You pass your single Vinkius token in the transport header, and the platform securely routes the requests to your Kubernetes API.

Your workflow manifests, parameters, and cluster metadata never persist on Vinkius servers. The connection runs inside an isolated V8 sandbox that executes requests ephemerally. Only transit data passes through, keeping your internal infrastructure private.

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