About Miro MCP Server
Miro MCP Server is an experimental MCP server for AI agents to work with a single Miro board. It generates tools from the Miro OpenAPI specification and supports a range of board items.
Key features
- 01Retrieve and update a board
- 02List, move, and delete items
- 03Create and edit sticky notes, text, shapes, and cards
- 04Manage connectors
- 05Add images, documents, embeds, and app cards
Use cases
- 01Update a configured board through an agent
- 02Find board items and change their position or parent
MCP support
The MCP server exposes Miro API operations as tools for MCP clients, scoped to a configured single board.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMiro MCP Server
An experimental Model Control Protocol (MCP) server for interacting with the Miro API and a single board.
Overview
This project provides a FastMCP server that exposes Miro API endpoints as tools that can be used by AI agents. It automatically generates tool definitions from the Miro OpenAPI specification, allowing AI agents to manipulate Miro boards programmatically.
Features
- Support for all major Miro board item types:
- Sticky notes
- Shapes
- Text
- Images
- Cards
- App cards
- Documents
- Embeds
- Connectors
Prerequisites
- Node.js
- A Miro account with API access
- A Miro API token
- A Miro board ID
Installation without Docker
-
Clone the repository:
git clone https://github.com/yourusername/mcp-server-miro.git cd mcp-server-miro -
Install dependencies:
npm install -
Create a
.envfile in the root directory with the following variables:MIRO_API_TOKEN=your_miro_api_token MIRO_BOARD_ID=your_miro_board_id # Optional, port PORT=3000
Usage
-
Start the server:
npm run devor
npm run build npm start -
The server will start at
http://localhost:8899/sse -
AI agents can now use the exposed Miro API tools through the MCP protocol
Using with Docker
# The exact command depends on your Docker version
docker compose up -d
docker-compose up -d
# Server should be up in default port or the one you chose
API Tools
The server exposes the following Miro API endpoints as tools:
Board Operations:
get_specific_board: Retrieves information about the current board.update_board: Updates the current board.
Generic Item Operations:
get_items: Retrieves a list of items on the board (supports filtering and pagination).update_item_position_or_parent: Updates the position or parent of a specific item.delete_item: Deletes a specific item (covers various types like sticky notes, text, shapes, etc.).
Sticky Note Operations:
create_sticky_note_item: Adds a sticky note.get_sticky_note_item: Retrieves a specific sticky note.update_sticky_note_item: Updates a specific sticky note.
Text Operations:
create_text_item: Adds a text item.get_text_item: Retrieves a specific text item.update_text_item: Updates a specific text item.
Shape Operations:
create_shape_item: Adds a shape item.get_shape_item: Retrieves a specific shape item.update_shape_item: Updates a specific shape item.
Card Operations:
create_card_item: Adds a card item.get_card_item: Retrieves a specific card item.update_card_item: Updates a specific card item.
Connector Operations:
create_connector: Adds a connector between items.get_connectors: Retrieves a list of connectors.get_connector: Retrieves a specific connector.update_connector: Updates a specific connector.delete_connector: Deletes a specific connector.
Document Operations:
create_document_item_using_url: Adds a document item from a URL.update_document_item_using_url: Updates a document item added from a URL. (Note: Getting specific documents is handled byget_items)
Embed Operations:
create_embed_item: Adds an embed item from a URL.update_embed_item: Updates an embed item. (Note: Getting specific embeds is handled byget_items)
Image Operations:
create_image_item_using_url: Adds an image item from a URL.update_image_item_using_url: Updates an image item added from a URL. (Note: Getting specific images is handled byget_items)
App Card Operations:
create_app_card_item: Adds an app card item.update_app_card_item: Updates an app card item. (Note: Getting specific app cards is handled byget_items)
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.