Provider REST API

18 actions

Connect Claude to Miro

Read and build Miro boards - sticky notes, shapes, text, frames, connectors and tags. Toolspoke puts 18 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Access token
Actions exposed: 18
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Miro
Open the marketplace in your workspace, add Miro to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with access token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Miro shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Miro asks for

Access token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Access tokenRequired: In Miro, open Profile settings → Your apps → Create new app. Leave “Expire user authorization token” unchecked, because an expiring token stops working after 1 hour and this field cannot refresh it (the choice cannot be changed after the app is created). Under Permissions tick boards:read and boards:write, then click “Install app and get OAuth token”, pick the team, and copy the token shown. It reaches only that team's boards and lasts until the app is uninstalled.; eyJtaXJvLm9yaWdpbiI6…

What Claude can do in Miro

18 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 6Reads
Writes: 9Writes
Destructive: 3Destructive

Reads

Fetches data and changes nothing.

list_boards
List the boards this token can reach, optionally narrowed by team, project, owner or a search text. Returns board ids, names, links and owners. Start here to find the board_id every other action takes.
get_board
Retrieve one board by id - its name, description, owner, team, sharing policy and link.
list_items
List the items on a board - sticky notes, shapes, text, frames, cards, images and more - with their content, position and parent frame. Pages with a cursor.
get_item
Retrieve one item on a board by id, with its type, content, style, position and geometry.
list_tags
List the tags defined on a board, with their ids, titles and colours.
list_board_members
List the people a board is shared with, with their names and roles.

Writes

Creates or updates something on the other side.

create_board
Create an empty board. It is private to its owner by default; this action sets no sharing policy, so it shares nothing.
copy_board
Copy an existing board, with all its items, into a new board. The original is not changed.
create_sticky_note
Add a sticky note to a board. Position is in board units relative to the board centre, or to the parent frame when parent_id is set.
create_shape
Add a shape to a board, optionally with text inside it - a box, circle, diamond, flowchart symbol and so on.
create_text
Add a free-standing text item to a board.
create_frame
Add a frame - a titled area that groups other items - to a board. Place items in it afterwards by passing its id as parent_id.
create_connector
Draw a line between two items already on the board, optionally with a caption on it.
create_tag
Define a new tag on a board. Attach it to cards or sticky notes with attach_tag.
attach_tag
Attach an existing tag to a card or sticky note. Up to 8 tags fit on one item.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_board
Delete a board. Destructive: the board and every item on it go to the team's trash and are removed for everyone who had access.
delete_item
Delete one item from a board. Destructive: other collaborators lose it too, and the API offers no undo.
share_board
Share a board with people by email and give them a role. Classified destructive rather than write: it hands people - possibly outside the team - access to everything on the board, and Miro emails them an invitation that cannot be recalled.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 18 actions above are the whole of it. A call to any other name is refused before it reaches Miro rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Miro of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Miro: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Miro. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Miro's own rate limits. A call that Miro refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Miro?

18 named actions: 6 that only read, 9 that write and 3 that delete or permanently alter something. They include list_boards, get_board and create_board. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Miro connector need?

Access token. The connector asks for access token. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Miro connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 18 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Miro connector not do?

The 18 actions above are the whole of it. A call to any other name is refused before it reaches Miro rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Miro of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Miro. An agent has to ask. Toolspoke does not retry, queue or back off around Miro's own rate limits. A call that Miro refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Miro's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Miro?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More design connectors

Browse all of them