Miro Whiteboard ConnectorSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@llmindset/mcp-miro)
A Model Context Protocol server to connect to the MIRO Whiteboard Application.
- Allows Board manipulation, sticky creation, bulk operations and more.
- Pass your OAuth key as an Environment Variable, or using the "--token" argument.
- Taking a photo of stickies and asking Claude to create MIRO equivalent works really well.
Installation
Installing via Smithery
To install MIRO Whiteboard Connector for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @llmindset/mcp-miro --client claude
Using mcp-get
You can install this package using mcp-get:
npx @michaellatman/mcp-get@latest install @llmindset/mcp-miro
Note - if you are using an old version of Windows PowerShell, you may need to run Set-ExecutionPolicy Bypass -Scope Process before this command.
Features
Resources
- Get Board Contents
Tools
- Create Sticky, Shape
- Read Board, Frame, Contents
- Bulk Create
Prompts
- Instruct on Board Coordinates etc.
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcp-miro": {
"command": "/path/to/node-or-npx",
"arguments": [
"/path/to/mcp-miro/build/index.js",
"--token","MIRO-OAUTH-KEY"
]
f70720368d83OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-miro --env MIRO_OAUTH_TOKEN=${MIRO_OAUTH_TOKEN} -- npx -y @llmindset/[email protected]{
"mcpServers": {
"mcp-miro": {
"command": "npx",
"args": [
"-y",
"@llmindset/[email protected]"
],
"env": {
"MIRO_OAUTH_TOKEN": "${MIRO_OAUTH_TOKEN}"
}
}
}
}Exposed tools (6)
3 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
bulk_create_items | write | Create multiple items on a Miro board in a single transaction (max 20 items) |
create_shape | write | Create a shape on a Miro board. Available shapes include basic shapes (rectangle, circle, etc.) and flowchart shapes (process, decision, etc.). Standard geometry specs: width and height in pixels (default 200x200) |
create_sticky_note | write | Create a sticky note on a Miro board. By default, sticky notes are 199x228 and available in these colors: gray, light_yellow, yellow, orange, light_green, green, dark_green, cyan, light_pink, pink, violet, red, light_blue, blue, dark_blue, black. |
get_frames | read | Get all frames from a Miro board |
get_items_in_frame | read | Get all items contained within a specific frame on a Miro board |
list_boards | read | List all available Miro boards and their IDs |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
node-fetch, yargs, @types/node, @types/yargs, typescript
# Load environment variables
Gates applied: no_behavioural_pass.
f70720368d83full audit observations/trust-audit/mcp-server/evalstate__miro-whiteboard-connector.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | f70720368d83 | SAFE | B | 89 | first audit |
Questions
What tools does Miro Whiteboard Connector expose?
6 in total: 3 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Miro Whiteboard Connector safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Miro Whiteboard Connector need?
It reads MIRO_OAUTH_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Miro Whiteboard Connector run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @llmindset/mcp-miro at 0.1.1.
How current is this page?
The grade is for one exact copy of the source (f70720368d83), read on 2026-10-07. The repository is watched and re-audited when it changes.