MCP server for controlling Miro whiteboards with AI assistants
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
git clone https://github.com/olgasafonova/miro-mcp-server{
"mcpServers": {
"miro": {
"command": "miro-mcp-server",
"env": {
"MIRO_ACCESS_TOKEN": "<miro_access_token>"
}
}
}
}MIRO_ACCESS_TOKENResumen de MCP Servers
# Miro MCP Server
Run your [Miro](https://miro.com) workshops, retros, and planning sessions from the command line. Read boards, create stickies, organize frames, and generate diagrams through Claude, Cursor, or any MCP client.
> **Community project** — Not officially affiliated with Miro. See [official options](#official-vs-community) below.
**98 tools** | **Single binary** | **All platforms** | **All major AI tools**
[](https://github.com/olgasafonova/miro-mcp-server/actions/workflows/ci.yml)
[](https://goreportcard.com/report/github.com/olgasafonova/miro-mcp-server)
[](https://opensource.org/licenses/MIT)
[](#token-efficiency)
[](#token-efficiency)
<video src="https://github.com/user-attachments/assets/a27c535e-f3b5-4a3a-ac3c-bea5fe7ebd0b" width="100%" autoplay loop muted playsinline></video>
---
## Documentation
| Document | Description |
|----------|-------------|
| [QUICKSTART.md](QUICKSTART.md) | Get running in 2 minutes |
| [SETUP.md](SETUP.md) | Full setup for all AI tools |
| [CONFIG.md](CONFIG.md) | Configuration reference |
| [PERFORMANCE.md](PERFORMANCE.md) | Optimization guide |
| [CHANGELOG.md](CHANGELOG.md) | Version history |
| [ERRORS.md](ERRORS.md) | Error handling & troubleshooting |
---
## Quick Start
### 1. Install
**Homebrew (macOS/Linux):**
```bash
brew tap olgasafonova/tap && brew install miro-mcp-server
```
**One-liner (macOS/Linux):**
```bash
curl -fsSL https://raw.githubusercontent.com/olgasafonova/miro-mcp-server/main/install.sh | sh
```
**Docker:**
```bash
docker pull ghcr.io/olgasafonova/miro-mcp-server:latest
```
**Manual download:** See [SETUP.md](SETUP.md) for all platforms
### 2. Get a Miro Token
1. Go to [miro.com/app/settings/user-profile/apps](https://miro.com/app/settings/user-profile/apps)
2. Create an app with `boards:read` and `boards:write` permissions
3. Install to your team and copy the token
### 3. Configure Your AI Tool
**Claude Code:**
```bash
claude mcp add miro -e MIRO_ACCESS_TOKEN=your-token -- miro-mcp-server
```
**Claude Desktop / Cursor / VS Code:** See [SETUP.md](SETUP.md)
**Cursor Marketplace:**
```bash
/add-plugin miro
```
> **Not working?** [Tell us what made it hard](https://github.com/olgasafonova/miro-mcp-server/issues/new?template=bug_report.yml) — even one sentence helps.
---
## What You Can Do
| Category | Examples |
|----------|----------|
| **Boards** | Create, copy, delete, update, share, list members |
| **Items** | Sticky notes, shapes, text, cards, app cards, images, documents, frames, docs |
| **Diagrams** | Generate flowcharts and sequence diagrams from Mermaid |
| **Docs** | Create and manage Markdown documents on boards |
| **Upload** | Upload and replace local image and document files on boards |
| **Tables** | Discover and inspect tables on boards |
| **Mindmaps** | Create mindmap nodes with parent-child relationships |
| **Code Widgets** | Syntax-highlighted code snippets on boards (v2-experimental) |
| **Bulk Ops** | Create multiple items at once, sticky grids |
| **Tags** | Create, attach, update, and organize with tags |
| **Groups** | Group, list, and manage item groups |
| **Connectors** | Connect items with styled arrows |
| **Export** | Board thumbnails, PDF/SVG export (Enterprise) |
### Voice Examples
- *"Add a yellow sticky saying 'Review PRs'"*
- *"Create a flowchart: Start → Decision → End"*
- *"What boards do I have?"*
- *"Share the Design board with jane@example.com"*
- *"Create a mindmap with 'Project Ideas' as root"*
---
## Companion Skill: `miro-workflow`
[](https://getskillcheck.com)
For Claude clients that support skills (Claude Code, Claude Desktop), this repo includes a [`miro-workflow`](skills/miro-workflow/) skill that describes how to assemble a few common board layouts from the atomic create-item tools.
Five layouts are covered:
| Workflow | Trigger phrase examples |
|----------|------------------------|
| **Sprint Board** | "set up a sprint board for sprint 42" |
| **Retrospective** | "create a retro board for our team" |
| **Brainstorm** | "brainstorm board for [topic]" |
| **Story Map** | "map the user journey for [product]" |
| **Kanban** | "kanban for our backlog" |
Each one specifies frame sizes, gap math, sticky placement, color conventions (the Miro API takes hex for frame fills and named values for stickies; two different vocabularies), and the tool-call order to follow. For single-tool calls ("add one sticky") or read-only inspection, the atomic tools are usually enough on their own.
The skill is new and likely needs adjustment as more layouts get exercised against real boards. Files live under [`skills/miro-workflow/`](skills/miro-workflow/). Claude Code auto-discovers skills from `~/Projects/claude-code-config/skills/`; for other hosts, follow your client's skill installation docs.
The badge above is awarded by [SkillCheck Pro](https://getskillcheck.com); this skill currently scores 92/100 with zero Critical issues and zero Warnings. Skills in this repo earn the badge at ≥90/100 with zero Critical and zero Warnings; below that bar, the badge is dropped until the skill passes again.
---
## Companion CLI: `miro-cli`
For shell-first usage, this server has a sibling: [`miro-cli`](https://github.com/olgasafonova/miro-cli). Same author, same Miro API coverage, different runtime. One verb per endpoint, JSON in and out, plus a local SQLite mirror for offline search. Reach for it when you're scripting Miro in CI, bulk-migrating stickies between boards, or querying boards offline without burning API quota.
The MCP server and the CLI overlap deliberately. Use the MCP server when an agent runtime is in the loop (Claude Code, Claude Desktop, Cursor). Use the CLI when bash, Makefiles, or CI are. Use both if you want.
Install:
```bash
brew install olgasafonova/tap/miro-cli
# or
go install github.com/olgasafonova/miro-cli/cmd/miro-cli@latest
```
---
## Companion MCP Apps server: `miro-mcp-apps`
If you want Miro data to render as interactive **UI** in the chat (cards, tables, color clusters, SVG graphs) instead of streamed JSON, there's a TypeScript sibling: [`miro-mcp-apps`](https://github.com/olgasafonova/miro-mcp-apps). Six tools built on the [MCP Apps extension](https://github.com/modelcontextprotocol/ext-apps) (SEP-1865), reusing the same `MIRO_ACCESS_TOKEN`. The two servers run side-by-side: this one for the 98-tool CRUD surface, that one for visual at-a-glance views.
| You want… | Use |
|---|---|
| Programmatic control: create/update/move/connect items, generate diagrams | `miro-mcp-server` (this repo) |
| Visual board summaries, sticky color clusters, connector graphs rendered inline | [`miro-mcp-apps`](https://github.com/olgasafonova/miro-mcp-apps) |
| Same in bash, CI, or a Makefile | [`miro-cli`](https://github.com/olgasafonova/miro-cli) |
The MCP Apps pattern is TypeScript-only today (Go SDK has no `ext-apps` helpers), which is why this companion lives in a separate repo instead of bolting onto the Go server.
---
## Token Efficiency
The full tool surface (98 tools) costs roughly **16.5K tokens** of preload — about 8.3% of a 200K Claude context. For sessions where that footprint matters, set `MIRO_TOOLS_PROFILE=essentials` in your client config; the server then registers a curated 15-tool subset (boards, list/find/search, sticky/text/frame/connector creation, list/get/update/delete items) plus one discovery meta-tool. Agents reach the rest via `miro_tool_search` on demand.
| Profile | Tools | Preload tokens (est.) | % of 200K context |
|---|---|---|---|
| `full` (default) | 98 | ~16,500 | 8.3% |
| `essentials` | 15 | ~2,400 | 1.2% |
Savings: **~13,100 tokens (84.5% reduction)** when you opt into `essentials`. Description tokens are exact (JSON-marshaled); schema cost is estimated at 200 bytes per tool. Reproduce locally with `go run ./cmd/token-count/`.
`miro_tool_search(query?, category?, limit?)` is registered in both profiles. It searches tool names, titles, descriptions, and categories with weighted keyword scoring (name 3×, title 2×, category 2.5×, description 1×), returns up to 50 matches, and never recommends itself. Use it when you don't know which tool to reach for, or to scope to a category before browsing. Empty query plus a category returns the category's tools alphabetically.
See [CONFIG.md](CONFIG.md) for the full env-var reference.
---
## All 98 Tools
<details>
<summary><b>Board Management (9)</b></summary>
| Tool | Description |
|------|-------------|
| `miro_list_boards` | List accessible boards |
| `miro_find_board` | Find board by name |
| `miro_get_board` | Get board details |
| `miro_get_board_summary` | Get board stats and item counts |
| `miro_get_board_content` | Get all board content for AI analysis |
| `miro_create_board` | Create a new board |
| `miro_copy_board` | Copy an existing board |
| `miro_update_board` | Update board name/description |
| `miro_delete_board` | Delete a board |
</details>
<details>
<summary><b>Board Members (5)</b></summary>
| Tool | Description |
|------|-------------|
| `miro_list_board_members` | List users with access |
| `miro_get_board_member` | Get member details |
| `miro_share_board` | Share board via email *(requires `MIRO_SHARE_ALLOWED_DOMAINS`; fail-closed by default)* |
| `miro_update_board_member` | Update member role *(Destructive: prompts before role escalation)* |
| `miro_remove_board_member` | Remove member from board |
> Sharing and role-change tools are guarded for prompt-injection safety. See [`SECURITY.md`](SECURITY.md#board-shariLo que la gente pregunta sobre miro-mcp-server
¿Qué es olgasafonova/miro-mcp-server?
+
olgasafonova/miro-mcp-server es mcp servers para el ecosistema de Claude AI. MCP server for controlling Miro whiteboards with AI assistants Tiene 26 estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala miro-mcp-server?
+
Puedes instalar miro-mcp-server clonando el repositorio (https://github.com/olgasafonova/miro-mcp-server) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar olgasafonova/miro-mcp-server?
+
Nuestro agente de seguridad ha analizado olgasafonova/miro-mcp-server y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene olgasafonova/miro-mcp-server?
+
olgasafonova/miro-mcp-server es mantenido por olgasafonova. La última actividad registrada en GitHub es de today, con 0 issues abiertos.
¿Hay alternativas a miro-mcp-server?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega miro-mcp-server en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/olgasafonova-miro-mcp-server)<a href="https://claudewave.com/repo/olgasafonova-miro-mcp-server"><img src="https://claudewave.com/api/badge/olgasafonova-miro-mcp-server" alt="Featured on ClaudeWave: olgasafonova/miro-mcp-server" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface