How to Use the Miro MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup handle comment threads on Miro?

Yes, the agent uses listcomments to read existing threads and createcomment to reply to specific parent IDs. This lets your agent participate in team discussions or log execution status right on the canvas.

Q: How does the agent discover existing boards?

The agent calls listboards to retrieve all accessible canvases along with their metadata. From there, it can select the target board ID and pass it to other tools to start modifying elements.

Spin up autonomous OpenAI Agents SDK workflows that manage Miro boards, cards, and sticky notes directly from your Python runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Miro MCP to OpenAI Agents SDK

Create your Vinkius account to connect Miro to OpenAI Agents 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin up and modify Miro boards on the fly

`create_board` lets your agent spawn new collaborative canvases instantly when a project kicks off. The agent gets back a unique board ID, view link, and edit link to share with your team. If the project scope changes, the agent updates metadata using `update_board` or discovers existing workspaces via `list_boards` to keep your workspace clean. You feed these board IDs directly into downstream tools to map out project timelines. The agent inspects individual board details with `get_board` to verify it has the correct workspace before running any bulk updates.

Populate canvases using OpenAI Agents SDK

`create_sticky_note` and `create_card` write structured items directly onto the canvas coordinate system. Your agent places these elements at precise x,y positions to build visual roadmaps, user story maps, or Kanban columns without manual intervention. For deeper content inspection, the agent uses `list_board_items` via the MCP connection to read what is already on the board, filtering by item types like text or connectors. If an item becomes obsolete or needs a complete rebuild, `delete_board_item` removes it from the canvas permanently.

Run secure MCP Server team collaborations

`add_board_member` assigns specific roles to team members directly from your agentic loop, keeping permissions locked down. The agent checks who has access using `list_board_members` and tracks active threads by pulling comments with `list_comments`. To keep the agent's identity transparent, `get_user_context` verifies the active API token and returns the current user profile. This ensures all automated actions, like posting a reply with `create_comment`, appear under the correct user identity in the board history.

Setup guide

Set up Miro MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Miro tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Miro tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Miro tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Miro Agent",
            instructions="You have access to Miro tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 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 MCP in OpenAI Agents SDK

Install the package using pip, then initialize the server streamable HTTP class with your Vinkius endpoint URL. Pass this instance into your Agent constructor using the mcp_servers parameter. Enable tool caching to avoid redundant schema lookups on startup.

Yes, the agent uses `list_comments` to read existing threads and `create_comment` to reply to specific parent IDs. This lets your agent participate in team discussions or log execution status right on the canvas.

You control tool exposure at the agent initialization step by filtering the registered tools array. This prevents the agent from calling destructive operations like `delete_board_item` unless explicitly authorized.

The agent calls `list_boards` to retrieve all accessible canvases along with their metadata. From there, it can select the target board ID and pass it to other tools to start modifying elements.

The server runs inside a zero-trust V8 sandbox on Vinkius, processing your board items and member lists entirely in memory. Ephemeral execution environments ensure no board layouts or comment histories are stored after the API call completes.

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