How to Use the Miro MCP in Google ADK

Q: How do I connect Miro to Google ADK?

Install the package and use McpToolset to load the Miro MCP Server. Pass that toolset into your LlmAgent constructor to give Gemini immediate access to tools like listboards.

Q: Can Google ADK read sticky notes from a Miro board?

Yes. The agent uses the listboarditems tool to fetch all visual elements on the canvas, feeding that content directly into Gemini's long-context window for analysis.

Q: How do I limit Google ADK to read-only Miro tools?

Use the toolnames filter during your toolset initialization. You can explicitly allow getboarddetails and listboards while blocking write tools like deleteboard.

Feed enterprise BigQuery data directly onto Miro canvases using Gemini, Google ADK, and this dedicated 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 MCP to Google ADK

Create your Vinkius account to connect Miro to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Translate BigQuery Datasets into Miro Sticky Notes

Running `create_sticky_note` allows your Gemini agent to map raw BigQuery analytics directly onto a visual canvas. By pairing this MCP Server with Google ADK, your Gemini agent can query cold analytics in Google Cloud and instantly write those insights onto a live board. This bridges the gap between raw data and executive brainstorming. Your agent reads the structured database, formats the critical metrics, and populates a new workspace created via `create_board` in a single run.

Analyze Giant Boards with Google ADK and Gemini

Calling `list_board_items` fetches thousands of sticky notes and shapes from massive boards directly into Gemini's long-context window. Instead of getting lost in the noise, the agent identifies patterns, groups similar ideas, and updates the canvas. This setup allows Gemini to digest the entire creative history of a project at once. The agent can clean up outdated workspaces by running `delete_board` once the synthesis is complete.

Restrict Google ADK Tool Access with Filters

Filtering your tools to expose only `list_boards` and `get_board_details` ensures strict enterprise security. When initializing the toolset in Google ADK, you can apply an optional `tool_names` filter to expose only read tools. This prevents Gemini from accidentally executing destructive actions. Your agent can safely inspect board collaborators with `list_board_members` without having the programmatic authority to delete or modify any visual assets.

Setup guide

Set up Miro MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Miro tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Miro_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Miro tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package and use `McpToolset` to load the Miro MCP Server. Pass that toolset into your `LlmAgent` constructor to give Gemini immediate access to tools like `list_boards`.

Yes. The agent uses the `list_board_items` tool to fetch all visual elements on the canvas, feeding that content directly into Gemini's long-context window for analysis.

Use the `tool_names` filter during your toolset initialization. You can explicitly allow `get_board_details` and `list_boards` while blocking write tools like `delete_board`.

While this server is hosted on Vinkius as an HTTP endpoint, the framework supports both Stdio and HTTP transports. For production, the managed HTTP endpoint is the most reliable way to connect.

Entirely. Your board metadata, including board names, organization details from `list_organizations`, and collaborator lists, is processed in transient memory. It is sent directly to the Miro API via secure HTTPS and is never persisted on Vinkius.

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