Miro

Create a table on a Miro board with specified columns. Supports text, select, multiselect, date, link, person, and number column types. This always creates a plain grid table. To produce a timeline, kanban, or tree, first create the table here, then call table_update_view to switch its layout. For a request like 'create a timeline/kanban/tree', do BOTH steps in sequence. 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. IMPORTANT: The created item is NOT shown to the user automatically. Do not restate its link, name, or details in your reply. After all content has been created, call the board_show tool once to display the result to the user.

table_create

Create multiple board items (and connectors between them) on a Miro board from DSL (Domain-Specific Language) text. PREREQUISITE: Call layout_get_dsl first to obtain the DSL format specification. Items are created using board-absolute coordinates. Frames are always created first, then all other items, then connectors last (so they can reference items by alias). Returns a list of any items that failed to be created. IMPORTANT: The created item is NOT shown to the user automatically. Do not restate its link, name, or details in your reply. After all content has been created, call the board_show tool once to display the result to the user.

layout_create

Delete a code widget from a Miro board.

code_widget_delete

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_get_dsl

Get image download URL for an image item from a Miro board.

image_get_url

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_explore

Read a code widget from a Miro board, returning its source code, language, title, and position.

code_widget_get

Fetch verbatim customer quotes for the feedback chunks returned by search_customer_feedback. Pass the chunk_ids of the summaries you found relevant to get the exact words customers used from those specific segments, with speaker, sentiment, strength, source, and a video link when the source is a recorded call.

insights_get_customer_feedback_quotes

Reserve one or more single-use upload slots for HTML screens. Set count to the number of screens in the prototype to reserve all slots in a single call instead of calling this once per screen. Returns one entry per slot, each with its own upload_url and token; uploads can run in parallel. PUT the raw HTML as the request body with Content-Type: text/html; no auth header. curl: curl -X PUT -H 'Content-Type: text/html' --data-binary @page.html '<upload_url>'. Max size: 1,048,576 bytes per screen. External http/https image URLs are fine; the server fetches them. Only local file references need pre-upload (see prototype_create's image_tokens). After each upload, pass its token to prototype_create, in the same order.

prototype_get_upload_url

Reserve one or more single-use upload slots for HTML slides. Set count to the number of slides in the deck to reserve all slots in a single call instead of calling this once per slide. Returns one entry per slot, each with its own upload_url and token. PUT every slide's HTML concurrently — start all uploads before waiting on any of them; uploading one at a time defeats the point of batching and is noticeably slower for the end user. PUT the raw HTML as the request body with Content-Type: text/html; no auth header. curl: curl -X PUT -H 'Content-Type: text/html' --data-binary @slide.html '<upload_url>'. Max size: 1,048,576 bytes per slide. External http/https image URLs are fine; the server fetches them. Only local file references need pre-upload (see slides_create_html's image_tokens). Slide sizing: size the slide via its <body> (e.g. <style>body{width:1280px;height:720px}</style>); the client renders and measures it. Slide label: include <meta name="screen:name" content="<label>"> in <head> so the slide gets a meaningful display label; without it a generic placeholder is used. Once all uploads complete, pass the full list of tokens to a single slides_create_html call, preserving upload order. A deck is always ONE slides_create_html call: if it has more than 30 slides, reserve slots across several calls here, then combine all tokens into that one create call — never split the deck into multiple create calls.

slides_get_upload_url_html

Get a single-use upload URL for a local image. Returns upload_url and a token. PUT the raw image bytes as the request body; set Content-Type to the image MIME type; no auth header. curl: curl -X PUT -H 'Content-Type: image/png' --data-binary @image.png '<upload_url>'. After upload, pass the returned token to any tool that accepts an image_token / image_tokens parameter — see each consumer tool's description for what it does with the upload. Max size: 6,000,000 bytes. Accepted types: image/bmp, image/gif, image/jpeg, image/png, image/svg+xml, image/vnd.adobe.photoshop.

image_get_upload_url

Get image data for an image item from a Miro board.

image_get_data

Read existing board items and return them as DSL text. When given a board URL, returns all supported top-level items (no frame children). When the URL targets a specific frame (via moveToWidget), returns the frame and its children. When the URL targets a non-frame item, returns just that item as DSL with full content. By default (mode=structured), DOCs and TABLEs are returned as shallow headers with read-only metadata (preview/length, schema/row count) so large boards stay token-light; open the DOC or TABLE by URL to read its full body. Pass mode=full to force inline DOC bodies and TABLE rows at any scope. Connectors between items in scope are returned as CONNECTOR lines (board and frame scope only). The returned DSL uses full Miro item URLs as ids and parent references; those URLs can be passed directly as miro_url to other tools (doc_get, table_list_rows, context_get, etc.) without modification, and fed back into layout_update for editing.

layout_read

List code widgets on a Miro board. Returns a paginated list of all code widget items on the board. Use the cursor from a previous response to retrieve the next page.

code_widget_list_items

Get guidance for writing Mermaid syntax for a diagram, including how to apply colors. Returns the rules and conventions needed to produce well-styled Mermaid diagrams. REQUIRED: Call this before calling diagram_create_mermaid to understand how to write the Mermaid syntax. When creating multiple diagrams of the same type in a conversation, you only need to call diagram_get_mermaid_instructions once and reuse the guidance for subsequent diagrams.

diagram_get_mermaid_instructions

Check whether a Miro create-result preview resource is ready. Returns pending until the preview is available. Tags: preview, resource.

preview_resource_poll

List items on a board with cursor-based pagination. For slide content, prefer slides_read_html over this tool.

board_list_items

List comments from a Miro board or a specific item on the board. Comments include author information, messages (original comment and replies), reactions, resolved status, and position. Use limit and offset for pagination. Use from_date and to_date to filter by creation time. Use resolved to filter by resolved status. IMPORTANT: The results are displayed to the user in an interactive navigator they can filter and paginate themselves. Do not restate, list, summarize, or describe the comments in your reply, and do not call this tool again for more pages unless the user explicitly asks. After calling this tool, respond with at most one short sentence (or no text at all) and use the returned data only to answer the user's explicit follow-up questions.

comment_list_comments

Read the content of a doc format item from a Miro board. Returns the markdown content and content version for use in subsequent edits.

doc_get

Use this tool first whenever the user mentions slides, a slide deck, or a presentation. Not for generic Miro frames — only HTML-based slides are covered. Read HTML slides from a Miro board. Returns slides with metadata (position, dimensions) and optionally their HTML markup. Covers both deck slides (HTML slides inside a slide deck container) and standalone HTML content widgets on the canvas. Non-HTML slide types are ignored. Provide deck_id to scope results to a specific deck, or omit to list all HTML slides on the board. If the query can be resolved using metadata alone (slide position, deck membership, dimensions), always call with include_html=false first to identify the minimal target set, then fetch include_html=true only for those slides. Only skip the metadata step when the query requires filtering on HTML content itself (e.g. 'find slides containing X text') — in that case fetch HTML directly, but scope to a specific deck_id where possible to avoid loading the entire board. When scoped to a deck_id, the response includes deck_modified_at (latest slide edit in that deck). Before iterating on a deck with slides_create_html's reference_deck_id, capture this value and pass it back as if_not_modified_since — that call rejects the edit if the deck changed after this read, so re-read and reapply before retrying.

slides_read_html

Get the history of a row's Latest Update field. The Latest Update field accumulates the text updates submitted for that row over time; this returns those entries ordered chronologically. Provide the table via its Miro URL and the target row via rowId (get rowIds from table_list_rows). Response includes for each entry: text, author_id (Miro user ID of the author), created_at and modified_at (ISO 8601 timestamps), plus the total number of entries.

table_get_latest_update_history

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, multiselect, 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_list_rows

Record a thumbs up/down rating a user gave on a Miro MCP UI response, attributed to the current MCP session. Tags: feedback, rating, ui.

record_ui_feedback

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. IMPORTANT: The results are displayed to the user in an interactive board browser they can search, filter, and paginate themselves. Do not restate, list, summarize, or describe the boards in your reply, and do not call this tool again for more pages unless the user explicitly asks. After calling this tool, respond with at most one short sentence (or no text at all) and use the returned data only to answer the user's explicit follow-up questions.

board_search_boards

Search feedback from your organization's customers, gathered from connected integrations (Gong calls, Zendesk tickets, etc.). Returns summaries of matching feedback segments. All inputs are optional. Provide 'query' for semantic search; omit it to browse the most recent feedback (optionally narrowed by filters), which suits open-ended questions like 'what are customers saying'. Combine filters to narrow results. To read the exact words customers used, pass the returned chunk_ids to get_customer_feedback_quotes.

insights_search_customer_feedback

Show a single interactive preview of items on a Miro board. Call this ONCE at the end of a board-building workflow, after all content has been created, instead of describing the board in text. Do not call it on an empty board or after every create step. Provide a URL with a moveToWidget or focusWidget parameter to preview that item, leave empty for multiple items. IMPORTANT: The board preview is displayed to the user in an interactive panel with its link. Do not restate the link or describe the board contents in your reply; respond with at most a brief confirmation.

board_show

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.

context_get

Update an existing code widget on a Miro board. All fields are optional — only the provided fields are updated.

code_widget_update

Edit content in an existing doc format item using find-and-replace. Provide the exact text to find (old_content) and the text to replace it with (new_content). By default, only the first occurrence is replaced. Use replace_all=true to replace all occurrences.

doc_update

Update the Mermaid code of an existing structured diagram on a Miro board. Use this tool when the user wants to iterate on a diagram that was previously created with diagram_create_mermaid. Provide the complete new Mermaid body - the existing code is fully replaced. Only works on diagrams created in structured (Mermaid) mode; diagrams created with the legacy diagram_create tool cannot be updated this way.PREREQUISITE: Call diagram_get_mermaid_instructions first to obtain guidance (including how to apply colors) for writing the Mermaid syntax.

diagram_update_mermaid

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"}]}]} IMPORTANT: The created item is NOT shown to the user automatically. Do not restate its link, name, or details in your reply. After all content has been created, call the board_show tool once to display the result to the user.

table_sync_rows

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"}. IMPORTANT: The created item is NOT shown to the user automatically. Do not restate its link, name, or details in your reply. After all content has been created, call the board_show tool once to display the result to the user.

table_update_view

Edit board items and connectors using find-and-replace on their DSL representation. Provide old_string (text to find in the current DSL) and new_string (replacement). Modified lines are updated, new lines create items/connectors, removed lines delete them. Use layout_read first to see the current DSL, then apply targeted edits. Unchanged items are not touched (no unnecessary API calls).

layout_update

Returns the identity of the current authenticated user.

user_who_am_i