How to Use the Miro (Visual Collaboration & Whiteboarding) MCP in Vercel AI SDK

Q: How do I connect the Miro (Visual Collaboration & Whiteboarding) MCP Server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into streamText or generateText to let your agent call Miro actions. Don't forget to close the client connection once the stream finishes.

Stream Miro boards directly into your React, Next.js, or Svelte frontend in real-time with 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 Miro (Visual Collaboration & Whiteboarding) MCP to Vercel AI SDK

Create your Vinkius account to connect Miro (Visual Collaboration & Whiteboarding) 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 Miro (Visual Collaboration & Whiteboarding) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build boards instantly during live chat with this MCP Server

`create_board` launches a brand new collaborative space directly from your user's chat prompt. Your web application triggers this action on the edge, bypassing slow backend middle layers to initialize a blank workspace in milliseconds. Once the workspace exists, your application streams the layout details straight to the client interface. Users see the canvas materialize on their screen without waiting for a full page refresh.

Populate sticky notes dynamically as the agent thinks

`create_sticky_note` places physical text components onto the active board coordinate system instantly. By using this tool inside a streaming text generation loop, your interface renders visual sticky blocks as the model generates ideas. This approach removes the standard loading spinner entirely. Ideas flow directly from the model's output stream into actual Miro objects, letting users watch their brainstorming session build itself in real time.

Audit active board members on the fly

`list_members` pulls the complete list of authorized team members currently assigned to a board. Your application calls this tool to verify who has access before displaying sensitive visual elements in the UI. Combining this live check with edge runtime speeds up permission validation. You keep your collaborative canvas secure while maintaining sub-millisecond response times for every active participant.

Setup guide

Set up Miro (Visual Collaboration & Whiteboarding) 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 Miro (Visual Collaboration & Whiteboarding) 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 Miro (Visual Collaboration & Whiteboarding) 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 Miro. 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 Miro (Visual Collaboration & Whiteboarding) 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 Miro (Visual Collaboration & Whiteboarding) MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into `streamText` or `generateText` to let your agent call Miro actions. Don't forget to close the client connection once the stream finishes.

Yes, the tool execution happens asynchronously on the edge. When the agent calls `create_sticky_note`, the tool result returns immediately, allowing the UI to render the new sticky note without freezing the user interface.

Vinkius handles the underlying token management through a single endpoint token. You pass this token in your Vercel AI SDK configuration, and the platform securely routes the requests to Miro's API.

Your application catches the error within the execution block, allowing the model to retry or inform the user. The edge function keeps running, ensuring a single failed API call doesn't crash the active chat session.

Your board IDs, sticky note content, and member lists never touch external databases. Vinkius runs the server in an isolated sandbox, ensuring that sensitive workspace data only passes directly between your application and Miro.

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