Miro MCP. Control visual whiteboarding with natural conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Miro Visual Collaboration & Whiteboarding connects your AI agent directly to Miro. You can manage entire digital workspaces—from project roadmaps to research flowcharts—using natural conversation.
Run `list_boards` to see all accessible boards, or use `create_sticky_note` to inject specific ideas onto a canvas without opening the app.
It treats your board like an API endpoint.
What your AI agents can do
Create board
Makes a brand new, blank collaborative Miro Board instantly.
Create shape
Puts a geometric shape (like a rectangle) onto an existing board at specific coordinates.
Create sticky note
Adds a new sticky note component with text to a designated Miro Board.
List all boards or fetch the specific setup details for one board by name or ID.
Create and place new sticky notes, rectangles, circles, or triangles at exact coordinates on a designated board.
List every distinct element—text blocks, shapes, images—physically attached inside a specific board for a full content audit.
Retrieve the list of active team members and verify their viewer or editor roles on any given board.
List the semantic organizational tags applied to a board, allowing you to track project metadata groupings efficiently.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Miro (Visual Collaboration & Whiteboarding) MCP Server: 8 Tools
These eight tools let your agent manage every aspect of a Miro board—from creating new canvases to auditing existing team members and content.
019d75d5create board
Makes a brand new, blank collaborative Miro Board instantly.
019d75d5create shape
Puts a geometric shape (like a rectangle) onto an existing board at specific coordinates.
019d75d5create sticky note
Adds a new sticky note component with text to a designated Miro Board.
019d75d5get board
Retrieves the specific, static configuration details for one targeted Miro Board.
019d75d5list boards
Lists all high-level Miro Boards that your account has access to globally.
019d75d5list items
Reads and lists every raw item—text or shape—attached inside a specified Miro Board ID.
019d75d5list members
Lists all team members who currently share access to a specific board.
019d75d5list tags
Retrieves the raw index groupings and semantic tags applied across a board for better organization.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Miro (Visual Collaboration & Whiteboarding), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Listen up. This server gives your AI agent full, programmatic control over Miro boards—it treats every single board like an API endpoint, letting you manage massive digital workspaces without ever opening the app or clicking a mouse.
When you need to figure out what's on the grid, your agent first needs to know which canvases exist. You can run list_boards to pull up a list of every high-level Miro Board that your account has access to globally. If you zero in on one specific board and need its exact setup details—the static configuration, for instance—you'll use get_board.
But if you want to start from scratch, or provision resources instantly for a new project, the create_board tool makes a brand new, blank collaborative Miro Board immediately. It's how you spin up a fresh canvas on demand.
Injecting content is where this thing shines. You don't have to guess coordinates; your agent can precisely place things. Use create_sticky_note and it’ll add a new sticky note component, complete with specific text, right onto the board you name. Need more than just notes? The create_shape tool lets you drop in any geometric shape—think rectangles, circles, or triangles—at exact coordinates on a designated board.
This means your agent can build structured diagrams or highlight specific areas by placing shapes exactly where you want them.
But building stuff is only half the battle; most of the time, you're auditing what already exists. To get a full content audit, your agent uses list_items. This reads and lists every distinct raw item—that includes text blocks, images, or shapes—physically attached inside a specific Board ID. You don’t just get a count; you get the details of every single element.
For organization tracking, running list_tags pulls up all the semantic index groupings and tags applied across the board, letting you track project metadata groupings efficiently. And if you need to know who's looking at this mess or who can edit it, list_members lists out all team members who currently share access to that specific board, along with their viewer or editor roles.
This means your agent doesn’t just talk about boards; it uses them. You tell your agent, 'List every text item on the Q4 Strategy board,' and it calls list_items, returning a clean list of content elements. You ask, 'Who's an editor on this thing?' and it runs list_members. It’s direct control over visual collaboration tools that used to require manual clicking and tedious exploration.
How Miro MCP Works
- 1 First, subscribe to the server and provide your Miro Access Token. This grants your agent connection rights.
- 2 Next, prompt your AI client (like Claude or Cursor) with a goal: 'List all my boards.' The agent calls
list_boards. - 3 Finally, when you identify the target board ID, you can proceed to action, such as calling
create_sticky_noteto add content.
The bottom line is that your AI client uses this server to run Miro's underlying API calls via natural language prompts.
Who Is Miro MCP For?
This tool is for the Product Manager who needs to track roadmap ideas across multiple sticky notes without clicking through dozens of boards. It’s for the Researcher who can instantly log insights from a meeting into a digital canvas, and the Engineering Lead who must audit board memberships before project handoffs.
Uses list_boards to see all roadmaps. They use the agent to gather feedback by running create_sticky_note on a specific feature board.
Needs to quickly log raw insights during a session. They call list_items to see what's already there, then use create_shape to draw an element representing a user flow step.
Runs list_members on a board before a meeting to verify that all necessary stakeholders have editor access. They also run list_tags for governance checks.
What Changes When You Connect
- Audit every piece of content instantly. Instead of visually scrolling through a board, use
list_itemsto get a raw list of every text block or shape attached. This saves hours of manual inspection. - Never forget who has access again. Run
list_memberson any board to see exactly which team members are viewers versus editors. Great for pre-review checks. - Quickly track project status. Use the agent to run
list_tagsand pull out all 'High Priority' items across multiple boards in seconds, giving you a clean metadata report. - Build new workspaces on demand. Need a fresh board? Call
create_boardto initialize a completely blank canvas with a custom title, ready for immediate use. - Add ideas without touching the mouse. Instead of opening Miro and clicking 'New Sticky Note,' just prompt your agent to run
create_sticky_note, specifying the text and target board.
Real-World Use Cases
Auditing a massive, messy roadmap
The Product Lead needs to know if all 'V2 Feature' requirements are documented. They ask their agent to run list_items on the main board ID. The agent returns a structured list of every text block and shape, allowing the lead to quickly identify gaps without scrolling through hundreds of notes.
Onboarding new team members
The Project Manager needs to confirm that the contractor has view-only access. They run list_members against the 'Core Architecture' board. The agent verifies the user status and provides a clear list of permissions, eliminating guesswork.
Quickly logging meeting insights
The UX Researcher is in a client call and has a key insight. Instead of pulling up Miro manually, they tell their agent to run create_sticky_note on the 'User Journey' board with the text 'Focus on mobile checkout flow.' The note appears instantly.
Preparing for a project handoff
The Engineering Team Lead needs to ensure the next department can access all planning assets. They run list_tags to see how the board is grouped, then use get_board to grab the full metadata summary before sharing it.
The Tradeoffs
Trying to find a specific piece of content
Opening Miro and manually clicking through different sections or using the built-in search, which often misses items buried under other shapes.
→
Run list_items on the board ID. This forces the agent to retrieve everything—every shape, every text block—into a clean, machine-readable list you can analyze.
Asking about collaborators without knowing scope
Just asking 'Who's on the board?' and getting vague answers that don't detail permissions.
→
Use list_members. This specific tool doesn't just list names; it gives you explicit viewer or editor status for every user.
Creating a new board, then forgetting the name
Manually creating five boards and losing track of which ID belongs to 'Q1 Marketing Strategy.'
→
Immediately run list_boards after creation. You get an indexed list of all your accessible boards, including their titles and IDs.
When It Fits, When It Doesn't
Use this server if your workflow is inherently visual, requires constant state changes (adding notes/shapes), or needs auditing capabilities on a whiteboard canvas. You need to know what is there and who can change it.
Don't use this if you simply need to manage documents, run surveys, or track simple task lists—use dedicated project management tools for that. If your goal is pure document storage (like Google Docs), Miro isn't the right fit. However, if you are using a structured database and occasionally need a visual 'sketchpad' attached, this server lets you bridge that gap seamlessly.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Finding specific information on a shared board shouldn't require clicking through five different tabs.
Today, finding one piece of data point—say, the original requirement for 'Feature X'—means opening Miro. You scroll past 50 other sticky notes. You check the shapes, you click into text blocks, and if the board is large, you end up guessing where it was placed.
With this MCP server, you skip all that. Your agent calls `list_items` on the target board ID. It pulls every single element—every note, every shape—and gives you a structured list of content metadata. You get the data instantly; no scrolling required.
The Miro MCP Server: Injecting visual elements with `create_sticky_note`.
Before this, if you wanted to add a sticky note to a specific spot on the board, you had to open the app and physically click at coordinates. It was slow, required multiple hand movements, and distracted from your main task flow.
Now, your agent handles it. You tell it: 'Add a sticky note saying X to Board Y.' The server executes `create_sticky_note` instantly, placing the content exactly where you need it. It’s direct, precise, and keeps your focus on what you're thinking.
Common Questions About Miro MCP
How do I list all my boards using list_boards? +
You simply tell your agent to run list_boards. It returns a comprehensive list of every board ID and title you have access to, letting you pick the right one for action.
Can I add a shape using create_shape? +
Yes. You prompt your agent to use create_shape, specifying the type (rectangle, circle, etc.) and the board ID. It places the geometric structure on the canvas immediately.
What is list_items for? +
list_items reads every piece of content—text blocks or shapes—physically attached to a specified board. Use it when you need a full inventory and can't rely on visual inspection.
How do I check who is viewing the board using list_members? +
Run list_members and provide the target board ID. The tool returns an enumeration of all active team members, detailing whether they are viewers or editors.
How do I add a new sticky note using create_sticky_note? +
The tool attaches a new sticky note component to your board. You pass the desired text and coordinates, and it injects the item onto the canvas so everyone sees it immediately.
What is list_tags for, and how do I read organizational tags? +
It retrieves all semantic organizational tags applied inside a board. This lets you see raw index groupings, which helps manage project metadata without manually inspecting every element on the canvas.
How can I provision a new board using create_board? +
This tool initializes a fresh collaborative Miro Board for you. You specify the title and context, and it creates a brand-new workspace ready for team ideation or planning sessions.
If I need full details, how do I use get_board? +
Using get_board pulls the static, explicit configuration of an existing board. This provides comprehensive metadata about the entire workspace layout, going beyond just listing the board's title.
Can I add a sticky note to a specific Miro board through my agent? +
Yes. Use the create_sticky_note tool by providing the Board ID and your text content. Your agent will inject a basic colored note onto the board's coordinate grid immediately, perfect for rapid ideation.
How do I see all the items currently on a board? +
The list_items tool retrieves all visual components physically attached to a board. Your agent will return a list of sticky notes, shapes, and text blocks, helping you audit the canvas content without opening the browser.
Can my agent list the team members who have access to my boards? +
Absolutely. Use the list_members tool with a specific Board ID. Your agent will report all active collaborators explicitly granted access, allowing you to verify viewer and editor permissions across your workspace.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Supabase Vector
Connect your AI to Supabase Vector. Execute pgvector semantic searches, manage embeddings, and run relational database queries directly from your terminal.
Redis Vector
Equip your AI to autonomously manage embeddings, run KNN similarity searches, and administrate vector indexes natively inside your Redis stack.
Upstash
Manage serverless Redis via Upstash REST API — execute commands, manage data structures and monitor your database from any AI agent.
You might also like
Baseten
Manage your Baseten AI models — orchestrate deployments, list secrets, and run serverless inference predictions autonomously.
Met Museum
Explore the Metropolitan Museum of Art's collection—search for artworks, list departments, and retrieve detailed object metadata and images.
Opsgenie
Automate incident management via Opsgenie — manage alerts, track on-calls, and coordinate incidents directly from any AI agent.