Trello

Developer tools

Trello for AI agents. Managed auth, ready-made tools.

Read boards and lists, and create, move and comment on Trello cards on behalf of each of your users.

About Trello

With the Trello connector, your agent works on each user’s own Trello boards. It can list boards, lists and cards, create a card, move it to another list, update it, comment on it and add a list, using only the tools your project allows.

Trello is a visual project tool that organizes work into boards, lists and cards.

Tools

What your agent can do in Trello.

Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Trello connection.

  • List boards

    Read
    trello_list_boards

    List the boards the user can see.

  • List lists

    Read
    trello_list_lists

    List the lists on a board.

  • List cards

    Read
    trello_list_cards

    List the cards on a board or in a list.

  • Create a card

    Write
    trello_create_card

    Create a card in a list.

  • Update a card

    Write
    trello_update_card

    Change a card's name, description, due date or list.

  • Add a comment

    Write
    trello_add_comment

    Comment on a card.

  • Create a list

    Write
    trello_create_list

    Add a new list to a board.

  • Archive a card

    Write
    trello_archive_card

    Archive a card.

Control

Limits you can set.

You decide what your agent may do in Trello, and Agent200 runs every call within those limits.

  • Turn single tools on or off

    Let the agent read boards and add cards, and switch off trello_archive_card so it can never archive one.

  • Restrict what the agent reaches

    Choose the endpoints and scopes a project may use, for example reading boards but not writing to them. A call outside them is refused.

Get started

Connect Trello
in three steps.

  1. 1

    Set up the SDK

    Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

    agent.js
    Conceptual example
    Set up the SDK with the Agent200 API key
    // One Agent200 API key covers every connector enabled for the project.
    const agent200 = new Agent200({
      apiKey: process.env.AGENT200_API_KEY,
    });
  2. 2

    Let your user connect Trello

    Each end user authorizes their own Trello account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

    connect.js
    Conceptual example
    Let an end user connect their account (managed OAuth)
    // Each end user authorizes their own Trello account, once.
    const connection = await agent200
      .user("user_123")
      .connect("trello");
    
    if (connection.authorizationUrl) {
      // Show this link to your user; Agent200 handles the rest.
      console.log(connection.authorizationUrl);
    }
  3. 3

    Run with the Trello tools

    Name the user, the model and the tools. The model decides which Trello tools to call, and Agent200 executes them with that user's connection.

    run.js
    Conceptual example
    Run a request with the connector's tools
    const result = await agent200
      .user("user_123")
      .run({
        model: "openai/gpt-5.6-sol",
        input: "Add a card to the Backlog list for the pricing page update",
        tools: ["trello"],
      });
    
    console.log(result.output);

Access

Sign-in and permissions.

  • Who signs in

    Each of your users, once, on Trello's own sign-in page. You never see or store their Trello password.

  • What access is requested

    The scopes the connection needs, such as reading or writing their boards, listed on Trello's authorization screen. Users can remove the app later from their Trello account settings.

For agents

Instructions for AI agents.

Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Trello connector and how to use it.

Agent brief
Connector: Trello, through Agent200. In code: "trello".
What it does: Read boards and lists, and create, move and comment on Trello cards on behalf of each of your users.
Page: https://www.agent200.com/connectors/trello/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Trello's own page, through the authorization link Agent200 returns. Never ask a user for a Trello password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: trello_list_boards, trello_list_lists, trello_list_cards. Write tools: trello_create_card, trello_update_card, trello_add_comment, trello_create_list, trello_archive_card. Name "trello" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/trello/framework/claude/
   https://www.agent200.com/connectors/trello/framework/chatgpt/
   https://www.agent200.com/connectors/trello/framework/claude-code/
   https://www.agent200.com/connectors/trello/framework/muse/
   https://www.agent200.com/connectors/trello/framework/grok-bot/
   https://www.agent200.com/connectors/trello/framework/openai-dots/
   https://www.agent200.com/connectors/trello/framework/claude-duet/
   https://www.agent200.com/connectors/trello/framework/hermes-agent/
   https://www.agent200.com/connectors/trello/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

This page is also available as Markdown, for agents and LLMs: /connectors/trello.md

Guides

Use Trello with the AI you build on.

Step-by-step setup for Trello with a specific model, assistant or agent framework.

FAQ

Trello and Agent200, answered.

Who handles the Trello OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Trello.

Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Trello connection, never another user's. It cannot reach anything the user or Trello has not authorized.

Can I limit what my agent can do in Trello?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

  • GitHub

    GitHub

    Read repositories and work with issues and pull requests as the connected user.

    Managed OAuth Developer tools
  • GitLab

    GitLab

    Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.

    Managed OAuth Developer tools
  • Bitbucket

    Bitbucket

    List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.

    Managed OAuth Developer tools
  • Jira

    Jira

    Search, create and transition Jira issues for the connected user.

    Managed OAuth Developer tools
200 OK

Start with Trello.
Your agent does the rest.

Your users connect their own Trello accounts. Agent200 handles the OAuth, the tokens and every tool call.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)