How to Use the Copy.ai MCP in Vercel AI SDK

Q: How do I trigger a Copy.ai workflow in Vercel AI SDK?

You use the runworkflow tool inside your generateText call. This connects your Vercel AI SDK app to the Copy.ai system so you can start tasks with a single function call.

Q: Can I see my Copy.ai run status in Vercel AI SDK?

Yes, you poll the getrunstatus tool to check if your task finished. It returns the current state so your Vercel AI SDK interface stays in sync with the backend.

Q: How do I list my Copy.ai workflows in Vercel AI SDK?

Call listworkflows to pull every available task into your app. This allows you to display a menu of options to your users.

Trigger Copy.ai workflows directly inside your Vercel AI SDK frontends for live content production and data updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Copy.ai MCP to Vercel AI SDK

Create your Vinkius account to connect Copy.ai 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 Copy.ai with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live workflow execution with Vercel AI SDK

Trigger `run_workflow` to start tasks immediately from your Next.js or React components. You get the status back as the system processes your request, letting you show live progress to the user. Your UI won't hang while waiting for the server to finish. Use `get_run_status` to poll the backend and update your frontend state without manual refreshing.

Fetch workflow schema for Vercel AI SDK

Call `get_workflow_details` to pull the exact input requirements for any process. You can build dynamic forms that adjust their fields based on the Copy.ai schema. This prevents runtime errors before the user even submits their data. You'll know exactly what the workflow expects, ensuring every request sent from your app is formatted correctly.

Manage brand assets in Vercel AI SDK

Use `list_brand_assets` to pull your stored voice profiles and Info Base items into your app. Your users can select their preferred brand settings from a dropdown populated by this MCP server. This creates a bridge between your application interface and the Copy.ai workspace. Your app becomes an extension of the workspace, pulling in the specific context needed for high-quality generation.

Setup guide

Set up Copy.ai 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 Copy.ai 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 Copy.ai 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 Copy.ai. 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 Copy.ai 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 Copy.ai MCP in Vercel AI SDK

You use the `run_workflow` tool inside your `generateText` call. This connects your Vercel AI SDK app to the Copy.ai system so you can start tasks with a single function call.

Yes, you poll the `get_run_status` tool to check if your task finished. It returns the current state so your Vercel AI SDK interface stays in sync with the backend.

The server provides the data that your Vercel AI SDK implementation handles. You feed the output into your stream so the user sees results as they appear.

Call `list_workflows` to pull every available task into your app. This allows you to display a menu of options to your users.

We only touch the workflow execution parameters and workspace metadata you explicitly request. Your Copy.ai data stays within your authorized connection to the Vercel AI SDK environment.

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