How do I get a Miro Access Token?

Go to [**Miro Developer Portal**](https://developers.miro.com/), create an app, and generate a Personal Access Token (PAT) or set up OAuth 2.0. PATs are simpler for personal use — go to your app settings and create a token under 'Personal Access Tokens'. Copy it immediately as it won't be shown again.

Can I create sticky notes programmatically?

Yes! Use `create_sticky_note` with the board ID and content text. Optionally set x,y coordinates on the canvas for precise positioning. The sticky note will appear on the board immediately and all collaborators will see it in real-time.

Can I manage board members via the API?

Yes! Use `list_board_members` to see who has access and their roles, and `add_board_member` to grant access to new users with a specific role (owner, admin, editor, commenter, viewer). The user must already have a Miro account.

Can I filter board items by type?

Yes! Use `list_board_items` with the type parameter to filter by: sticky_note, card, shape, text, connector, image, embed, frame, document, or mind_map. This is useful for finding specific widget types without loading all board content.

Miro MCP Server for Pydantic AI 14 tools — connect in under 2 minutes

Name: Miro
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 14 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Miro through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Miro "
            "(14 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Miro?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Miro MCP Server

Connect your Miro account to any AI agent and take full control of your visual collaboration through natural conversation.

Pydantic AI validates every Miro tool response against typed schemas, catching data inconsistencies at build time. Connect 14 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Board Management — List, create, update and inspect boards with their descriptions, owners and permissions
Item Operations — Browse all widgets on a board (sticky notes, cards, shapes, texts, connectors, images) with their content and positions
Content Creation — Create sticky notes and cards programmatically with custom content and canvas positions
Member Management — List board members and add new users with specific roles (owner, admin, editor, commenter, viewer)
Comments — Read and add comments on boards for async collaboration feedback

The Miro MCP Server exposes 14 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Miro to Pydantic AI via MCP

Follow these steps to integrate the Miro MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 14 tools from Miro with type-safe schemas

Why Use Pydantic AI with the Miro MCP Server

Pydantic AI provides unique advantages when paired with Miro through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Miro integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Miro connection logic from agent behavior for testable, maintainable code

Miro + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Miro MCP Server delivers measurable value.

Type-safe data pipelines: query Miro with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Miro tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Miro and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Miro responses and write comprehensive agent tests

Miro MCP Tools for Pydantic AI (14)

These 14 tools become available when you connect Miro to Pydantic AI via MCP:

add_board_member

Requires the board ID and user ID. Optionally set the role (owner, admin, editor, commenter, viewer). The user must already have a Miro account. Add a member to a Miro board

create_board

Requires the board name and optionally a description. Returns the created board with its ID, view link and edit link. Create a new Miro board

create_card

Requires the board ID and card title. Optionally set a description and x,y position. Cards are structured content widgets with title and description fields. Create a card widget on a Miro board

create_comment

Requires the board ID and comment content. Optionally reply to an existing comment by providing its ID as parent_id. Add a comment to a Miro board

create_sticky_note

Requires the board ID and the sticky note content (text). Optionally set the x,y position on the canvas. Returns the created sticky note with its ID and position. Create a sticky note on a Miro board

delete_board_item

Provide the board ID and item ID. WARNING: this action is irreversible. Delete an item from a Miro board

get_board

Provide the board ID (found in the board URL or from list_boards). Get details for a specific Miro board

get_board_item

Provide the board ID and item ID. Get details for a specific item on a Miro board

get_user_context

Returns user ID, name, email, avatar and account type. Use this to verify your access token is working correctly and to see which user identity the API calls will appear as. Get the authenticated Miro user context

list_board_items

) placed on a Miro board. Each item includes its type, ID, content, position, rotation, size and style. Optionally filter by item type (sticky_note, card, shape, text, connector, image, embed, frame, document, mind_map) and set a limit. List items (widgets) on a Miro board

list_board_members

Each member shows their user ID, name, email, role (owner, admin, editor, commenter, viewer) and permission level. Optionally set a limit. List members of a Miro board

list_boards

Each board includes its ID, name, description, creation date, owner and permissions. Optionally set a limit on the number of results. Use this to discover boards before accessing their content. List Miro boards accessible by the user

list_comments

Each comment includes its ID, content text, author info, creation date and parent comment ID (for replies). Optionally set a limit. List comments on a Miro board

update_board

Provide the board ID and the new name and/or description. Only provided fields will be updated. Update a Miro board name or description

Example Prompts for Miro in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Miro immediately.

"Show me all the sticky notes on my Sprint Planning board."

"Create a new board called 'Q2 OKRs' with a description 'Quarterly objectives and key results'."

"Add a sticky note to my board saying 'Meeting notes: Discussed API versioning strategy' at position x:100, y:200."

Troubleshooting Miro MCP Server with Pydantic AI

Common issues when connecting Miro to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Miro + Pydantic AI FAQ

Common questions about integrating Miro MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Miro MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.