How to integrate Miro MCP with Vercel AI SDK v6

This guide walks you through connecting Miro to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Miro agent that can create a new board for marketing brainstorm, list all boards owned by your team, show members of the q2 planning board through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Miro account through Composio's Miro MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Miro

Oauth2

Miro is a collaborative online whiteboard platform for teams to brainstorm, design, and manage projects visually. It streamlines teamwork by enabling real-time idea sharing, diagramming, and workflow planning in a single space.

73 Tools

Managed auth

Connect Miro without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

This guide will help you understand how to give your Vercel AI SDK agent real control over a Miro account through Composio's Miro MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Miro with

ChatGPT OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenCode Cursor VS Code OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Miro integration
Using Composio's Tool Router to dynamically load and access Miro tools
Creating an MCP client connection using HTTP transport
Building an interactive CLI chat interface with conversation history management
Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

streamText: Core function for streaming responses with real-time tool support
MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
OpenAI Provider: Native integration with OpenAI models

What is the Miro MCP server, and what's possible with it?

The Miro MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Miro account. It provides structured and secure access to your whiteboards, so your agent can create new boards, manage board content, organize workflows, and collaborate visually—all on your behalf.

Automated board creation and setup: Instantly instruct your agent to create new Miro boards with specific names and descriptions for projects, brainstorming, or workshops.
Visual content management: Ask your agent to add, retrieve, or delete items such as shapes, sticky notes, app cards, or document items from any board, keeping your workspace tidy and up to date.
Efficient team and member management: Have your agent fetch and list all members of a board so you can easily track collaborators and manage access.
Seamless board organization and retrieval: Let your agent search and retrieve boards by team, owner, or keyword to keep your workspace organized and easy to navigate.
Connector and tag insights: Direct your agent to get details on connectors and tags used within boards, helping you map relationships and categorize content visually.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS

Prerequisites

Before you begin, make sure you have:

Node.js and npm installed
A Composio account with API key
An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install required dependencies

bash

npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

@ai-sdk/openai: Vercel AI SDK's OpenAI provider
@ai-sdk/mcp: MCP client for Vercel AI SDK
@composio/core: Composio SDK for tool integration
ai: Core Vercel AI SDK
dotenv: Environment variable management

Set up environment variables

bash

OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

OPENAI_API_KEY: Your OpenAI API key for GPT model access
COMPOSIO_API_KEY: Your Composio API key for tool access
COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

What's happening:

We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
The dotenv/config import automatically loads environment variables
The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["miro"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Miro tools
The create method takes the user ID and specifies which toolkits should be available
The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
This session provides access to all Miro-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript

const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();

What's happening:

We're creating an MCP client that connects to our Composio Tool Router session via HTTP
The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
The type: "http" is important - Composio requires HTTP transport
tools() retrieves all available Miro tools that the agent can use

Initialize conversation and CLI interface

typescript

let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to miro, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

What's happening:

We initialize an empty messages array to maintain conversation history
A readline interface is created to accept user input from the command line
Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

What's happening:

We use streamText instead of generateText to stream responses in real-time
toolChoice: "auto" allows the model to decide when to use Miro tools
stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
onStepFinish callback displays which tools are being used in real-time
We iterate through the text stream to create a typewriter effect as the agent responds
The complete response is added to conversation history to maintain context
Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Miro and Vercel AI SDK:

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["miro"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to miro, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Miro agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

Real-time streaming responses for a better user experience with typewriter effect
Live tool execution feedback showing which tools are being used as the agent works
Dynamic tool loading through Composio's Tool Router with secure authentication
Multi-step tool execution with configurable step limits (up to 10 steps)
Comprehensive error handling for robust agent execution
Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

TOOLS

Supported Tools

Every Miro action and event your agent gets out of the box.

Attach Tag To Item

Tool to attach an existing tag to a specific item on a Miro board.

Create App Card Item

Tool to add an app card item to a board.

Create Board

Tool to create a new board.

Create Card Item

Tool to create a card item on a Miro board.

Create Connector

Tool to create a connector (edge/arrow) that links two existing board items.

Create Document Item

Tool to create a document item on a Miro board by providing a URL to the document.

Create Document Item Using File From Device

Tool to create a document item on a Miro board using a URL to the document.

Create Embed Item

Tool to create an embed item on a Miro board by providing a URL to embed content (YouTube videos, websites, etc.

Create Frame Item

Tool to add a frame item to a Miro board.

Create Group

Tool to create a group on a Miro board by grouping multiple items together.

Create Image Item Using Local File

Tool to create an image item on a Miro board by uploading a local image file.

Create Items in Bulk

Tool to create multiple items on a Miro board in a single request.

Create Mind Map Node (Experimental)

Tool to create a mind map node on a Miro board.

Create Shape Item

Tool to create a shape item on a Miro board.

Create Sticky Note Item

Tool to create a sticky note item on a Miro board.

Create Tag

Tool to create a new tag on a Miro board.

Create Text Item

Tool to create a text item on a Miro board.

Delete App Card Item

Tool to delete an app card item from a board.

Delete Card Item

Tool to delete a card item from a board.

Delete Connector

Tool to delete a specific connector from a board.

Delete Document Item

Tool to delete a document item from a board.

Delete Embed Item

Tool to delete an embed item from a board.

Delete Frame Item

Tool to delete a frame item from a Miro board.

Delete Group

Tool to delete a group from a board.

Delete Image Item

Tool to delete an image item from a board.

Delete Item

Tool to delete a specific item from a board.

Delete Mind Map Node (Experimental)

Tool to delete a mind map node from a board.

Delete Shape Item

Tool to delete a shape item from a board.

Delete Sticky Note Item

Tool to delete a sticky note item from a board.

Delete Tag

Tool to delete a specific tag from a board.

Delete Text Item

Tool to delete a text item from a board.

Get All Groups

Tool to retrieve all groups on a Miro board with cursor-based pagination.

Get App Card Item 2

Tool to retrieve a specific app card item by its ID from a Miro board.

Get Board Items

Tool to list items on a Miro board (shapes, stickies, cards, etc.

Get Board Members

Tool to retrieve a list of members for a board.

Get Boards V2

Tool to retrieve accessible boards with optional filters.

Get Card Item

Tool to retrieve a specific card item from a Miro board.

Get Connector

Tool to retrieve a specific connector by its ID.

Get Connectors

Tool to retrieve a list of connectors on a board.

Get Document Item

Tool to retrieve a specific document item from a Miro board by its ID.

Get Embed Item

Tool to retrieve a specific embed item from a board by its ID.

Get Frame Item

Tool to retrieve a specific frame item from a Miro board.

Get Group By ID

Tool to retrieve a specific group by its ID.

Get Image Item

Tool to retrieve a specific image item from a board.

Get Item Tags

Tool to retrieve tags attached to a specific item on a Miro board.

Get Mind Map Node

Tool to retrieve a specific mind map node from a board.

Get Mind Map Nodes (Experimental)

Tool to retrieve mind map nodes from a Miro board.

Get oEmbed Data

Tool to retrieve oEmbed data for a Miro board.

Get Shape Item

Tool to retrieve a specific shape item from a Miro board by its ID.

Get Specific Board

Tool to retrieve detailed information about a specific board by its ID.

Get Specific Board Member

Tool to retrieve details of a specific board member.

Get Specific Item

Tool to retrieve a specific item from a Miro board by its ID.

Get Sticky Note Item

Tool to retrieve a specific sticky note item from a board by its ID.

Get Tag

Tool to retrieve details of a specific tag on a board.

Get Text Item

Tool to retrieve a specific text item from a Miro board by its ID.

List Board Tags

Tool to list all tags on a Miro board.

Get Organization Context

Retrieves the organization associated with the current access token.

Share Board

Tool to share a board by inviting users via email.

Update App Card Item 2

Tool to update an app card item on a Miro board.

Update Board

Tool to update properties of a specific board.

Update Board Member

Tool to update the role of a specific board member.

Update Card Item

Tool to update a card item on a Miro board.

Update Connector

Tool to update an existing connector on a Miro board.

Update Document Item

Tool to update a document item on a Miro board.

Update Embed Item

Tool to update an embed item on a board.

Update Frame Item

Tool to update a frame item on a Miro board.

Update Group

Tool to update a group on a Miro board with new items.

Update Image Item

Tool to update an existing image item on a board.

Update Item Position or Parent

Tool to update an item's position or parent frame on a Miro board.

Update Shape Item

Tool to update an existing shape item on a Miro board.

Update Sticky Note Item

Tool to update a sticky note item on a Miro board.

Update Tag

Tool to update a tag on a board.

Update Text Item

Tool to update a text item on a Miro board.

FRAMEWORKS

How to build Miro MCP Agent with another framework

ChatGPT

Use Miro MCP with ChatGPT

OpenAI Agents SDK

Use Miro MCP with OpenAI Agents SDK

Claude Agent SDK

Use Miro MCP with Claude Agent SDK

Claude Code

Use Miro MCP with Claude Code

Claude Cowork

Use Miro MCP with Claude Cowork

Codex

Use Miro MCP with Codex

Cursor

Use Miro MCP with Cursor

OpenClaw

Use Miro MCP with OpenClaw

Hermes

Use Miro MCP with Hermes

CLI

Use Miro MCP with CLI

Google ADK

Use Miro MCP with Google ADK

LangChain

Use Miro MCP with LangChain

Mastra AI

Use Miro MCP with Mastra AI

LlamaIndex

Use Miro MCP with LlamaIndex

CrewAI

Use Miro MCP with CrewAI

OpenCode

Use Miro MCP with OpenCode

VS Code

Use Miro MCP with VS Code

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Figma

Oauth2Api Key

Figma is a collaborative interface design tool for teams and individuals. It streamlines design workflows with real-time collaboration and easy sharing.

Abyssale

Api Key

Abyssale is a creative automation platform for generating images, videos, GIFs, PDFs, and HTML5 content programmatically. It streamlines and scales visual content production for marketing, design, and operations teams.

Alttext ai

Api Key

AltText.ai is a service that generates alt text for images automatically. It helps boost accessibility and SEO for your visual content.

Bannerbear

Api Key

Bannerbear is an API-driven platform for generating images and videos automatically at scale. It helps businesses create custom graphics, social visuals, and marketing assets using powerful templates.

FAQ

Frequently asked questions

With a standalone Miro MCP server, the agents and LLMs can only access a fixed set of Miro tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Miro and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Miro tools.

Yes, absolutely. You can configure which Miro scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Miro data and credentials are handled as safely as possible.

Start with Miro.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Miro tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Miro MCP with Vercel AI SDK v6

Connect Miro without auth hassles

Introduction

Also integrate Miro with

TL;DR

What is Vercel AI SDK?

What is the Miro MCP server, and what's possible with it?

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

Handle user input and stream responses with real-time tool feedback

Complete Code

Conclusion

Supported Tools

How to build Miro MCP Agent with another framework

ChatGPT

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

Cursor

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

OpenCode

VS Code

Explore Other Toolkits

Figma

Abyssale

Alttext ai

Bannerbear

Frequently asked questions

What are the differences in Tool Router MCP and Miro MCP?+

Can I use Tool Router MCP with Vercel AI SDK v6?+

Can I manage the permissions and scopes for Miro while using Tool Router?+

How safe is my data with Composio Tool Router?+

Start with Miro.It takes 30 seconds.

Teams ship real agents on Composio