M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

MCP Server Trello

Community
MCP server providing AI agents full access to Trello boards
How to install ↓ Compare GitHub source repository ↗
Category
Collaboration #16 of 55
Stars
★ 446 Very popular
Transport
stdio (local process)
Runtime
Node.js · Bun 1.0.0+
Credentials
API key / credential required
License
MIT
Last commit
Tools
35
58FMRS · C

This server provides comprehensive Trello integration with 57 tools covering checklists, attachments, comments, and custom fields. It supports dynamic board and workspace selection and built-in rate limiting. The only potential drawback is reliance on Bun and high-level API credentials.

Strongest · Documentation 15/20 Weakest · Reliability 7/20

Reliability
7/20
Security and permissions
10/20
Maintenance
12/20
Documentation
15/20
Setup experience
14/20
Why each score
Reliability 7/20
The README and manifest describe a stdio server with many tools, but no source code, CI workflow, or test files were supplied, so startup, MCP initialization, and tool behavior cannot be verified. Corrupted/typo-ridden code snippets in the README ('mbs;', 's;') further reduce confidence. The score is below 10 because the happy path is only documented, not demonstrated, and evidence of testing and error handling is absent.
Security and permissions 10/20
Credentials are passed via environment variables TRELLO_API_KEY and TRELLO_TOKEN, marked as secret in the manifest, and all install examples use placeholders. The optional TRELLO_ALLOWED_WORKSPACES restriction supports least privilege. However, no source code was available to inspect for logging, secret storage, or data-flow disclosure; destructive operations (archive/delete) have no described confirmation step, and the Trello token itself is highly privileged.
Maintenance 12/20
The repository is not archived, has an MIT license, the manifest shows npm version 1.8.1, and the README references a CHANGELOG, indicating ongoing maintenance. However, there is no evidence of issue-response timeliness, dependency update cadence, or a security-response channel, and the 21 open issues are not contextualized.
Documentation 15/20
The README is extensive: installation, authentication, environment variables, tool parameter examples, date formats, rate limiting, error handling, and client configuration for Claude Desktop/Claude Code are covered, with layered docs including CHANGELOG and skill references. Deductions come from corrupted code blocks, missing troubleshooting guidance, and the claimed 57 tools not being fully enumerated.
Setup experience 14/20
The install path is clear: published on npm, one-line npx/bunx command, copy-paste configurations for multiple clients, and complete environment-variable instructions. However, the static calibration caps setup at 15 without CI/test execution evidence, and the supplied material lacks such evidence; Bun/Node prerequisites are also not fully specified.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the networkChanges third-party account data

Best for

  • Teams that need AI agents to access Trello and manage project tasks.
  • Developers who want to automate board workflows with AI assistants.

Not for

  • Scenarios requiring only read-only access without real-time interaction.
  • Environments with high performance requirements that cannot tolerate Bun dependency.

Required permissions

  • Requires Trello API key and token to access Trello data on behalf of the user.
  • By default, can access all boards and workspaces the token has access to.
  • Optional restriction to specific workspaces via environment variable TRELLO_ALLOWED_WORKSPACES.

Risks and side effects

  • Risk of API credential leakage; handle keys and tokens securely.
  • AI may accidentally perform destructive operations, such as deleting cards or comments.
  • Improper use may trigger Trello rate limits.

Setup

Before you start

Runtime：Node.js · Bun 1.0.0+

TRELLO_API_KEY requiredsecret Required Trello API key, obtained at trello.com/app-key; treat as a secret.
TRELLO_TOKEN requiredsecret Required Trello token, generated from the same page (trello.com/app-key) using your API key; treat as a secret.
Other optional settings (3)
TRELLO_BOARD_ID optional Optional (deprecated) default board ID, found in the board URL; can be changed later with set_active_board.
TRELLO_WORKSPACE_ID optional Optional initial workspace ID, found in workspace settings or via the list_workspaces tool.
TRELLO_ALLOWED_WORKSPACES optional Optional comma-separated workspace IDs that restrict MCP access to only those workspaces.
  1. Obtain your Trello API key and token from https://trello.com/app-key.
  2. Add the server to your MCP client configuration, e.g., Claude Desktop config.
  3. Start the server using bunx or npx, setting environment variables TRELLO_API_KEY and TRELLO_TOKEN.
claude_desktop_config.json 
{
  "mcpServers": {
    "trello": {
      "command": "bunx",
      "args": [
        "@delorenj/mcp-server-trello"
      ],
      "env": {
        "TRELLO_API_KEY": "your-trello-api-key",
        "TRELLO_TOKEN": "your-trello-token"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "trello": {
      "command": "bunx",
      "args": [
        "@delorenj/mcp-server-trello"
      ],
      "env": {
        "TRELLO_API_KEY": "your-trello-api-key",
        "TRELLO_TOKEN": "your-trello-token"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add trello -e TRELLO_API_KEY=your-trello-api-key -e TRELLO_TOKEN=your-trello-token -- bunx @delorenj/mcp-server-trello

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After installing, restart the client and the tool list should include tools like get_acceptance_criteria, list_boards, and set_active_board; calling list_boards and seeing your Trello boards confirms the connection works.

Troubleshooting

  1. Common troubleshooting checks: - Ensure TRELLO_API_KEY and TRELLO_TOKEN are correct. - Check network connectivity to Trello API. - If rate limited, wait and retry. - Review error messages to confirm board/list/card IDs are valid.

Things to try

Once connected, you can ask your AI assistant things like:

  • List all my Trello boards and set my development board as the active board.
  • Show all cards across the lists on the current board and organize them by status.
  • Add a new acceptance criteria item to this card's checklist, then check completion progress.
  • Read the recent comments on this card and add a reply note.

Tools 35

get_checklist_items read-only
Get all items from a checklist by name.
add_checklist_item writes
Add a new item to an existing checklist.
find_checklist_items_by_description read-only
Search for checklist items containing specific text.
get_acceptance_criteria read-only
Get all items from the 'Acceptance Criteria' checklist.
get_checklist_by_name read-only
Get a complete checklist with all items and completion percentage.
update_checklist_item writes
Update an existing checklist item.
delete_checklist_item destructive
Delete an existing checklist item.
get_card read-only
Get comprehensive details of a specific Trello card.
Show 27 more tools
get_cards_by_list_id read-only
Fetch all cards from a specific list.
get_lists read-only
Retrieve all lists from a board.
get_recent_activity read-only
Fetch recent activity on a board.
add_card_to_list writes
Add a new card to a specified list.
update_card_details writes
Update an existing card's details.
archive_card writes
Send a card to the archive.
add_list_to_board writes
Add a new list to a board.
archive_list writes
Send a list to the archive.
update_list writes
Update a list's name, archive state, subscription state, or board.
update_list_position writes
Update the position of a list on the board.
get_my_cards read-only
Fetch all cards assigned to the current user.
move_card writes
Move a card to a different list.
attach_image_to_card writes
Attach an image to a card directly from a URL.
attach_file_to_card writes
Attach any type of file to a card from a URL or a local file path.
download_attachment read-only
Download an attachment from a card by ID.
add_comment writes
Add a comment to a Trello card.
update_comment writes
Update an existing comment on a card.
delete_comment destructive
Delete a comment from a card.
get_card_comments read-only
Retrieve all comments from a specific card.
list_boards read-only
List all boards the user has access to.
set_active_board writes
Set the active board for future operations.
list_workspaces read-only
List all workspaces the user has access to.
set_active_workspace writes
Set the active workspace for future operations.
list_boards_in_workspace read-only
List all boards in a specific workspace.
get_active_board_info read-only
Get information about the currently active board.
get_board_custom_fields read-only
Get all custom field definitions on a board.
update_card_custom_field writes
Set or clear a custom field value on a card.

Use cases

Manage boards, lists, and cards via AI assistants.
Extract acceptance criteria from cards.
Automate comments and attachment operations.
Switch between multiple workspaces and boards dynamically.

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

A Model Context Protocol (MCP) server that gives AI agents full access to your Trello boards — cards, lists, checklists, attachments, comments, custom fields, and workspaces — with built-in rate limiting, type safety, and workflow-level tools you won't find in a plain API wrapper, like acceptance-criteria extraction and checklist dependency queries. 57 tools, one npx install, powered by Bun.

Similar servers

Compare with other MCP servers

Source revision e17a471ad6e6 Data synced 2026-10-19 Read the FMRS scoring method