How to Use the Workato MCP in Vercel AI SDK

Q: How do I check job status with Workato and Vercel AI SDK?

You call listrecipejobs via the MCP tool. Your client gets a list of recent executions, letting you stream the job statuses back to the user's UI in real time.

Q: Can I see all available API collections using Workato and Vercel AI SDK?

Yep. The getapicollections tool lists every API collection exposed by Workato. Your agent can use this data to guide the user on what external services are connectable.

Q: What kind of connection details does Workato provide for Vercel AI SDK?

The server provides listappconnections, which lists all application connections configured in your Workato account. This helps your agent audit the credentials available.

Q: Does Workato support folder listing with Vercel AI SDK?

Yes, you can use listworkatofolders to list all organizational folders across your Workato account. It's a simple way to map out the overall structure.

See automated data appear live in your UI 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 Workato MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Workato recipes and jobs instantly.

When you call `mcpClient.tools()`, you get access to critical visibility tools. You can pull a list of recent job executions using `list_recipe_jobs` so the end user sees status updates immediately, not after some loading spinner. This real-time data flow is perfect for showing users exactly what's happening behind the scenes. Your client pulls execution details from `list_recipe_jobs`, making the AI feel genuinely connected to Workato’s backend.

List all app connections and folders.

Need to know what data sources are available? You can run `list_app_connections` to see every configured application connection. It's also useful for auditing structure; use `list_workato_folders` to map out the account’s organizational layout. This allows your agent to validate credentials before running a full workflow, so you don't waste time on recipes that hit dead ends.

Get details on specific Workato recipes.

Want the deep dive? The tool `get_recipe_details` retrieves everything about one specific recipe. You can pass this data directly to your streaming function, making it look like the AI is consulting a live documentation page. This means you don't just tell the user what Workato does; you show them *how* a particular recipe works, step by step.

Setup guide

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

You call `list_recipe_jobs` via the MCP tool. Your client gets a list of recent executions, letting you stream the job statuses back to the user's UI in real time.

Yep. The `get_api_collections` tool lists every API collection exposed by Workato. Your agent can use this data to guide the user on what external services are connectable.

The server provides `list_app_connections`, which lists all application connections configured in your Workato account. This helps your agent audit the credentials available.

Yes, you can use `list_workato_folders` to list all organizational folders across your Workato account. It's a simple way to map out the overall structure.

This server handles application connection details; specifically, it touches information about configured application connections and recipes. You can use `list_app_connections` for that.

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