Connect Trello to Claude Code
Let Claude create cards and move them across lists in Trello. From the terminal, inside the sessions where you already work.
How do you connect Trello to Claude Code?
Claude Code reaches outside tools through MCP servers. To connect Trello, you add a Trello MCP server: a small hosted service that exposes Trello's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Trello account. No API keys pasted into config files.
claude mcp add --transport http trello https://your-connector-url/mcpThen run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.
What can Claude Code do in Trello once connected?
Full read-write Trello access lets Claude create cards in the right list, move them between lists as work progresses, set due dates and members, apply labels, and add checklists or comments once you approve. The board upkeep that used to mean dragging cards by hand happens where the work already lives.
- Create a card in a chosen list with a description, due date, and members
- Move a card between lists as it progresses through the workflow
- Apply or remove labels to categorize and triage cards
- Add a checklist or check off items to track subtasks on a card
- Post a comment on a card to capture context from a discussion
- Set or change the due date and assigned members on existing cards
One connector, every Claude surface
The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Trello access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.
Build it yourself, or have it built?
If you live in the terminal, you can absolutely write your own MCP server against the Trello API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Trello changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Trello connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.
Frequently asked questions
Does the same Trello connector work in claude.ai and Claude Code?
Do I need to host or maintain anything myself?
Is it safe to give a coding agent write access to Trello?
More on the Trello connector
Tell us what you run. We'll build the connector.
Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.
