Miro MCP Server
Connect to the Miro MCP server to create boards, build layouts and diagrams, edit docs and tables, and work with comments using AI agents on Gumloop, Claude, or Cursor.
Try Miro now
Type what you want done. Sign in and run it live with an AI agent.
|
Miro
Installation
Set up the Miro MCP server in Gumloop
Do this once to provision your hosted server URL.
Create a Gumloop account
To use this MCP, you need a Gumloop account. If you don't have one yet, sign up and start a 14-day free trial.
Add and authorize the Miro server
In Gumloop, open Connectors and add Miro. You'll be sent to Miro's sign-in screen to grant access. The credential is stored securely in Gumloop.
Then use it in your client
Use in GumloopUse Miro in an agent
Once Miro is set up, just open any Gumloop agent, add Miro as a connector, and start chatting with the agent.
Tools (32)
User Who Am I
Returns the identity of the current authenticated user.
Board Search Boards
Search and list boards accessible to the current user, scoped to their team. Returns board metadata — name and URL — suitable for navigating to a specific board or discovering relevant boards before operating on them. Use this tool when the user wants to find a board by name or description, or discover which boards are available before using other board tools. Supports offset-based pagination.
Board List Items
List items on a board with cursor-based pagination. For slide content, prefer slides_read_html over this tool.
Board Create
Create a new Miro board. IMPORTANT: Always confirm with the user before creating a board. This action creates a new board and cannot be undone.
Context Explore
Explore high-level items on a Miro board. Returns a list of frames, documents, prototypes (interactive design mockups with multiple UI screens), individual prototype screens, tables, and diagrams with their URLs and titles. Use this to discover what's on a board before retrieving detailed content with context_get.
Context Get
Get text context from a Miro board or a specific item on a board. When a plain board URL is provided (no moveToWidget parameter): returns an AI-generated overview summarizing the entire board contents. When a URL with moveToWidget/focusWidget parameter is provided: returns detailed content for that specific item. For documents: returns Markdown content of the document. For prototype screens: returns HTML markup representing the UI/layout of that specific screen within an interactive design prototype. For prototype containers: returns AI-generated map of all screens with navigation flow. For frames: generates AI summary of frame contents. For tables: returns formatted table data. For diagrams: returns Mermaid code when available, otherwise an AI-generated description and analysis of the diagram structure.
Diagram Get Dsl
Get the DSL (Domain-Specific Language) format specification for a diagram type. Returns the rules, syntax, color guidelines, and examples needed to write valid DSL for creating diagrams. Supported diagram types: flowchart, uml_class, uml_sequence, entity_relationship. REQUIRED: Call this before calling diagram_create to understand the expected DSL format. When creating multiple diagrams of the same type in a conversation, you only need to call diagram_get_dsl once and reuse the format specification for subsequent diagrams.
Diagram Create
Create a diagram on a Miro board from DSL (Domain-Specific Language) text. PREREQUISITE: Call diagram_get_dsl first to obtain the DSL format specification for the diagram type you want to create. Then generate DSL text following that specification and pass it to this tool. Supported diagram types: flowchart, uml_class, uml_sequence, entity_relationship. Coordinates: when the URL has no item target, x/y are board-absolute (board center is (0, 0)). When the URL targets a frame via moveToWidget, the diagram is created INSIDE that frame and x/y are relative to the frame's top-left corner; (0, 0) is the frame's top-left and the diagram must fit within the frame's width and height. If no board URL is provided, a new board will be created. IMPORTANT: Always confirm with the user before creating a new board.
Table Create
Create a table on a Miro board with specified columns. Supports text, select, date, link, and person column types. Coordinates: when the URL has no item target, x/y are board-absolute (board center is (0, 0)). When the URL targets a frame via moveToWidget, the table is created INSIDE that frame and x/y are relative to the frame's top-left corner; (0, 0) is the frame's top-left and the table must fit within the frame's width and height. If no board URL is provided, a new board will be created. IMPORTANT: Always confirm with the user before creating a new board.
Table List Rows
Get rows from a Miro table with column metadata. Each row includes a stable rowId that uniquely identifies it within the table. rowIds persist across sorting, insertion, and deletion — use them to target specific rows in table_sync_rows. Supports filtering by column value. Returns text, select, and latest_update columns. Best practice: always use filter_by and limit when possible.Examples: next item that is not done: {"filter_by": {"Status":["To do", "In progress"]}, "limit": 1}top 5 high priority tasks: {"filter_by": {"Priority":["High"]}, "limit": 5} Response includes for each row: rowId (stable row identifier), cells (array of columnTitle, valueType, content, options, latest_update_text, latest_update_author_id). Pagination: Use 'limit' to control page size (default 10) and 'next_cursor' to fetch subsequent pages. The cursor is opaque and encodes pagination state. IMPORTANT: Do not change 'filter_by' when using a cursor from a previous response, as this will result in an error. To apply a different filter, start a new pagination sequence (no cursor).
Table Sync Rows
Add or update rows in a Miro table. To update existing rows, include rowId in the row object. rowId precisely targets a single row. Get rowIds from table_list_rows. Rows without rowId are inserted as new. Examples: Update a specific row by rowId: {"rows": [{"rowId": "3", "cells": [{"columnTitle": "Status", "value": "Complete"}]}]} Insert new rows: {"rows": [{"cells": [{"columnTitle": "Task", "value": "New task"}, {"columnTitle": "Status", "value": "Not Started"}]}]}
Table Update View
Update a Miro table widget's view: switch it to a grid table, timeline, or kanban board. The table keeps its data; only how it is displayed changes. Choose layout: - table: plain grid (use to revert from another layout) - timeline: lays records out on a time axis; optionally set the visible window with timeline_start_date and timeline_end_date - kanban: groups records into columns; set group_by_column to the name of a select column to group by (omit for an ungrouped board) Only provide config that matches the chosen layout. Examples: switch to kanban grouped by Status: {"layout": "kanban", "group_by_column": "Status"}. Switch to a timeline for 2026: {"layout": "timeline", "timeline_start_date": "2026-01-01T00:00:00Z", "timeline_end_date": "2026-12-31T00:00:00Z"}.
What is Miro MCP?
The Miro MCP server gives AI agents access to your Miro boards. That means agents can search and list your boards, read a board’s context and items, create new boards, build layouts of sticky notes, shapes, text, cards, frames, and connectors from a simple DSL, generate diagrams, create and edit docs and tables, add images and code widgets, build interactive prototypes from HTML screens, and read and post comments. It works across the objects a working Miro board is made of, so an agent can build and read a canvas the way your team does.
Think about the last workshop or sprint planning session you ran. You copied notes onto a board by hand, rebuilt the same retro template that you did last quarter, and chased down comments scattered across a dozen frames. Instead, try using an AI agent: Describe the board you want, and your AI agent will create it for you.
MCP stands for Model Context Protocol, an open standard that connects AI agents to the tools you already use. The Miro MCP server is the bridge between your Miro account and your agent. Once you connect it on Gumloop, you can create boards, read their contents, and act on feedback just by chatting with your AI agent.
Related MCP servers
Notion MCP Server
Server for interacting with Notion
Confluence MCP Server
Server for interacting with Confluence Cloud
Asana MCP Server
Interact with Asana projects, tasks, and workspace management
Trello MCP Server
Interact with Trello to manage boards, lists, cards, checklists, labels, custom fields, and comments
JIRA MCP Server
Interact with JIRA for project management, issue tracking, and user information access.
Slack MCP Server
Interact with Slack channels and messages
What you can do with Miro MCP on Gumloop
Create and find boards
Confirm who you’re connected as, search and list the boards you can access, and create a new board (the agent confirms with you first). Your agent finds the right canvas without you clicking through Miro.
Read and summarize a board
Pull a board’s text context and explore its high-level items (frames, docs, tables, diagrams, prototypes), or list items with pagination, so an agent can summarize what a canvas contains.
Build layouts from a simple DSL
Read the layout DSL spec, then create or edit board items and the connectors between them with layout_create and layout_update, and read a board back as DSL. This is how an agent places sticky notes, shapes, text, cards, and frames from a plain description.
Generate diagrams
Fetch the diagram DSL spec and create flowcharts, sequence flows, and other diagrams directly on the canvas.
Create and edit docs and tables
Create structured docs (and read or find-and-replace their content), and create tables, read their rows, upsert rows, and switch a table’s view between grid, timeline, and kanban.
Add images, code widgets, and prototypes
Upload and place images, create syntax-highlighted code widgets (with full read, update, delete, and list support), and build interactive prototypes from one or more HTML screens.
Read and post comments
List the comments on a board or item, and create a new comment at a specific spot on the canvas, so an agent can leave context or flag something for the team. (The server lists and creates comments; it does not reply to or resolve threads.)
How to connect the Gumloop Miro MCP Server
- 1
Create a Gumloop account
Sign up at gumloop.com. Every new account starts with a 14-day free trial.
- 2
Add the Miro MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Miro in your AI workflows
That's it. Your AI agent can now build boards, read canvases, generate diagrams, and post comments on your behalf. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Miro MCP use cases
Product managers keep roadmaps current with Miro MCP
Ask your agent to search for the roadmap board, read its items, and update a status table so the canvas matches reality before review. When a stakeholder leaves a comment, have your agent surface it and post a follow-up note on the board.
Designers turn ideas into canvases with Miro MCP
Describe the flow you have in mind and let your agent lay out frames, shapes, and text from DSL to sketch the first pass. Point it at an image to drop supporting visuals onto the board, then ask it to reorganize the layout as the concept evolves.
Workshop facilitators run sessions with Miro MCP
Tell your agent to create a fresh board and build a template of sticky-note columns and headers. After the session, ask it to read the board and summarize it so you leave with clear next steps instead of a wall of notes.
Engineering leads diagram systems with Miro MCP
Have your agent generate a sequence flow or architecture diagram from DSL, add a code widget with the relevant snippet, and read an existing diagram back to update it as the design changes.
Teams turn concepts into clickable prototypes with Miro MCP
Ask your agent to assemble a prototype from HTML screens and place it on the board, so stakeholders can click through an idea in the same canvas where the team is working.
Why use Gumloop for Miro MCP
Skip the OAuth setup
You don’t register an app or manage tokens by hand. Gumloop handles the Miro OAuth flow, so connecting your account takes a couple of clicks.
Works with multiple MCP clients
Use the Miro MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Miro with 100+ other integrations
Chain Miro with any other MCP integrations in a single agent, so a board summary can flow into your docs, chat, and project tools automatically.
Enterprise-grade and trustworthy
The Miro MCP server respects your existing board permissions and access controls. For details on Gumloop’s security practices, see trust.gumloop.com.
Start with a free trial
You can test the Miro MCP integration during Gumloop’s 14-day free trial before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Miro agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.