# Miro for AI agents. Managed auth, ready-made tools.

> Read Miro boards and add sticky notes, cards, frames and boards on behalf of each of your users.

- Page: https://www.agent200.com/tools/miro/
- Category: Files and knowledge
- Authentication: Managed OAuth
- Identifier in code: `miro`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: Miro, through Agent200. In code: "miro".
What it does: Read Miro boards and add sticky notes, cards, frames and boards on behalf of each of your users.
Page: https://www.agent200.com/tools/miro/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Miro's own page, through the authorization link Agent200 returns. Never ask a user for a Miro password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: miro_list_boards, miro_get_board, miro_list_items. Write tools: miro_create_board, miro_create_sticky_note, miro_create_card, miro_create_frame, miro_create_connector. Name "miro" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/miro/framework/claude/
   https://www.agent200.com/tools/miro/framework/chatgpt/
   https://www.agent200.com/tools/miro/framework/claude-code/
   https://www.agent200.com/tools/miro/framework/muse/
   https://www.agent200.com/tools/miro/framework/grok-bot/
   https://www.agent200.com/tools/miro/framework/openai-dots/
   https://www.agent200.com/tools/miro/framework/claude-duet/
   https://www.agent200.com/tools/miro/framework/hermes-agent/
   https://www.agent200.com/tools/miro/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Miro connector, your agent works on each user's Miro boards: it finds boards, reads the sticky notes, cards and shapes on them, and adds new items, frames and boards. Each user connects their own Miro account through managed OAuth and picks the team to connect, and your agent stays within that team's boards and the operations your project allows.

Miro is an online whiteboard where teams brainstorm, plan and map ideas together.

## Miro tools

- **List boards** (`miro_list_boards`, read): Find the boards the user can access, by name.
- **Get a board** (`miro_get_board`, read): Read a board's name, description and owner.
- **List items** (`miro_list_items`, read): Read the sticky notes, cards, shapes, text and frames on a board.
- **Create a board** (`miro_create_board`, write): Create a new board in the team.
- **Add a sticky note** (`miro_create_sticky_note`, write): Place a sticky note with text on a board.
- **Add a card** (`miro_create_card`, write): Place a card with a title and description on a board.
- **Add a frame** (`miro_create_frame`, write): Add a frame to group items on a board.
- **Connect items** (`miro_create_connector`, write): Draw a line between two items on a board.

## Limits you can set

**Turn single tools on or off.** Allow `miro_list_items` and the other read tools, and switch off `miro_create_board` if your agent should only work on existing boards.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Miro

Each end user authorizes their own Miro account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Miro account, once.
const connection = await agent200
  .user("user_123")
  .connect("miro");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Miro tools

Name the user, the model and the tools. The model decides which Miro tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Summarize the sticky notes on our retro board",
    tools: ["miro"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Miro's own page, choosing the team to connect. You never see or store their Miro password.

**What access is requested.** Read access to boards, and write access when your agent adds items, as shown on Miro's consent screen. Miro's own board sharing still decides what the user can reach.

## Example requests

- "Summarize the sticky notes on our retro board"
- "Add a card for each open bug to the sprint board"
- "Create a board for the Q1 planning workshop"
- "Group these ideas into frames by theme"

## Guides: Miro with your AI framework

- [Miro + Claude](https://www.agent200.com/tools/miro/framework/claude.md): Connect Miro to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Miro + ChatGPT](https://www.agent200.com/tools/miro/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds Miro into your own agent with OpenAI's models and the Agent200 SDK.
- [Miro + Claude Code](https://www.agent200.com/tools/miro/framework/claude-code.md): Have Claude Code build a Miro agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [Miro + Muse](https://www.agent200.com/tools/miro/framework/muse.md): Connect Miro to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Miro + Grok Bot](https://www.agent200.com/tools/miro/framework/grok-bot.md): Connect Miro to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Miro + OpenAI Dots](https://www.agent200.com/tools/miro/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Miro agent with OpenAI's models and the Agent200 SDK.
- [Miro + Claude Duet](https://www.agent200.com/tools/miro/framework/claude-duet.md): Connect Miro to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Miro + Hermes Agent](https://www.agent200.com/tools/miro/framework/hermes-agent.md): Connect Miro to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Miro + OpenClaw](https://www.agent200.com/tools/miro/framework/openclaw.md): Connect Miro to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the Miro OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Miro.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Miro connection, never another user's. It cannot reach anything the user or Miro has not authorized.

### Can I limit what my agent can do in Miro?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [Google Drive](https://www.agent200.com/tools/google-drive.md): Find, read and organize the files in each user's Drive.
- [OneDrive](https://www.agent200.com/tools/onedrive.md): Search, read, upload and share OneDrive files, including Word, Excel and PowerPoint documents, on behalf of each of your users.
- [Dropbox](https://www.agent200.com/tools/dropbox.md): Search, read, upload and organize Dropbox files, and create shared links, on behalf of each of your users.
- [Notion](https://www.agent200.com/tools/notion.md): Search, read and write Notion pages and databases on behalf of each of your users.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
