Provider REST API

18 actions

Connect Claude to Trello

Read and update Trello boards, lists, cards, comments and checklists. 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: API key and token
Actions exposed: 18
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Trello
Open the marketplace in your workspace, add Trello to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key and 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. Trello 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 Trello asks for

API key and 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.

API keyRequired: trello.com/power-ups/admin → New (create a Power-Up for your Workspace) → API key → Generate a new API key. The key identifies the Power-Up; the token below is what grants access.; 32 hex characters
TokenRequired: On the same API key page, follow the "Token" link and click Allow. The token acts as you on every board you can see, so create it from the account the agent should act as.; ATTA…

What Claude can do in Trello

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: 10Reads
Writes: 7Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

list_boards
List the boards the token's member belongs to. Takes no arguments and needs a token that can actually read boards, which is why an install tests itself with it rather than with a profile lookup.
get_board
Read one board by id or by the short link in its URL (trello.com/b/<shortLink>/…), including its labels and open lists.
list_lists
List the lists (columns) on a board, in board order. The list ids here are what create_card and update_card take.
list_board_cards
List the open cards on a board, across every list.
list_list_cards
List the cards in one list, in list order.
get_card
Read one card by id or by the short link in its URL (trello.com/c/<shortLink>/…), with its checklists, members and the board and list it sits in.
search
Search cards and boards the token can see. Accepts Trello's search operators, e.g. "board:Roadmap is:open due:week label:bug".
list_labels
List a board's labels with their names and colours. Label ids here are what create_card and update_card take in label_ids.
list_board_members
List the members of a board. Member ids here are what create_card and update_card take in member_ids.
list_card_comments
List the comments on a card, newest first. Comments are other people's words, so the response is not written to the audit log.

Writes

Creates or updates something on the other side.

create_card
Create a card in a list. Only list_id is required; name and desc are what most callers want. due and start are ISO 8601 timestamps.
update_card
Change a card: rename it, edit its description, move it to another list, set or complete its due date, or archive it with closed: true (reversible with closed: false). member_ids and label_ids replace the card's current set.
add_comment
Add a comment to a card as the token's member. Mentioned members (@username) are notified.
create_list
Add a list (column) to a board.
archive_list
Archive a list, or restore it with archived: false. Reversible, which is why this connector offers it and no list delete.
add_checklist
Add a checklist to a card. Returns the checklist id that add_checklist_item takes.
add_checklist_item
Add an item to a checklist.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_card
Delete a card permanently, with its comments, checklists and attachments. There is no undo; to take a card off the board reversibly, use update_card with closed true instead.

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 Trello 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 Trello 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 Trello: 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 Trello. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Trello's own rate limits. A call that Trello refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Trello?

18 named actions: 10 that only read, 7 that write and 1 that delete or permanently alter something. They include list_boards, get_board and list_lists. 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 Trello connector need?

API key and token. The connector asks for api key and 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 Trello 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 Trello connector not do?

The 18 actions above are the whole of it. A call to any other name is refused before it reaches Trello 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 Trello 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 Trello. An agent has to ask. Toolspoke does not retry, queue or back off around Trello's own rate limits. A call that Trello 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 Trello'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 Trello?

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 project management connectors

Browse all of them