Integration
Use Miro with Claude, GPT, Gemini and more
Connect Miro once, then ask any model in llmwise to read from it and act in it: 78 actions, with every write shown to you before it runs.
Actions (toolkit version 20260917_00) checked against Composio's Miro toolkit page.
Short answer
Miro connects to llmwise in one click, and every model can then use its 78 actions: 29 that read and run on their own, and 49 that write and ask you first (16 of them every time). On paid plans, included in the message price.
Try it: Miro in one message
Send this with any model. The model finds Miro's actions for the job and runs them, and the reply shows each one.
Group the sticky notes on my Retro board in Miro into themes and add one sticky note per theme.
| Action | In llmwise |
|---|---|
| Get Board Items | Reads: runs without asking |
| Create Sticky Note Item | Writes: asks first |
The reads run straight away; the write waits on an approval card with Allow and Deny, and shows what it will do first.
What the model can do in Miro
78 actions in all. Below: the 23 Composio marks as Miro's main ones, and 7 more. The other 48 are there too, and the model finds them when a job needs one.
Reads: runs without asking
- Get Board Members
- Get Boards V2
- Get Frame Item
- Get Tag
- Get Organization Context
Writes: asks first
- Attach Tag To Item
- Create Board
- Create Card Item
- Create Connector
- Create Document Item
- Create Image Item from URL
- Create Image Item Using Local File
- Create Items in Bulk
- Create Sticky Note Item
- Create Tag
- Create Text Item
- Remove Tag From Item
- Update Embed Item
- Update Tag
- Create App Card Item
- Create Document Item Using File From Device
- Create Embed Item
- Create Frame Item
- Create Group
- Create Mind Map Node (Experimental)
- Create Shape Item
Always asks first
- Delete App Card Item
- Delete Frame Item
- Delete Shape Item
- Delete Text Item
What asks first, and why
Reading needs no approval. Anything that writes asks first, and sending, deleting, payments and sharing always ask.
In Miro, that means delete app card item, delete frame item, delete shape item, and delete text item always wait for your yes.
Always allow can switch off the question for one of Miro's 33 other writes, and a reply that has read outside content asks again anyway. One reply runs up to 10 actions, each result read up to 50,000 characters.
Where your Miro data goes
Each action runs through Composio and Miro's own service, which receive its inputs; the result is shown in your chat and saved with it. Composio holds the sign-in, encrypted. More in the Privacy Policy.
More apps
100+ apps connect in one click · 1,500+ in Composio's catalog. Every app with its own page, or add a remote server of your own with the MCP client.
Questions
How do I connect Miro to llmwise?
In Settings → Connectors, press Connect next to Miro and sign in on Miro's own page: one click, no setup. Composio holds the connection, and llmwise never sees your password. On a paid plan.
Which AI models work with Miro, and what does it cost?
Any of the 15 models in llmwise, from GLM 5.3 Flash to Claude Fable 5.1: Miro's actions are the same whichever you pick. Connectors are on the paid plans (Pro ($20 a month), Max ($50 a month), Ultra ($100 a month), and Studio ($200 a month)), included in the message price.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.