Control Trello with Natural Language
The Trello MCP Server lets AI assistants read, create, move, and manage Trello boards, lists, and cards, including archiving and board deletion.
Why it matters
Integrate your Trello boards with AI assistants to manage tasks, lists, and cards using natural language commands. Streamline project management by interacting with Trello through your preferred AI interface.
Outcomes
What it gets done
View and read Trello boards, lists, and cards.
Create, move, and archive Trello cards and lists.
Add comments to Trello cards.
Manage Trello boards via natural language.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-trello-mcp-server | bash Capabilities
Tools your agent gets
Show all open Trello boards
Read lists and cards from a specific board
Create a list
Create a new card in a specific list
Move a card to another list
Add a comment to a card
Archive a card
Archive a list
Overview
Trello MCP Server
This MCP server gives AI assistants full read/write access to Trello: listing and reading boards, creating and moving cards, adding comments, archiving, and deleting boards, exposed as natural-language-callable tools and as board resources. Use it to let an AI assistant manage Trello boards on your behalf. Review delete_board and archive actions before confirming them in shared workspaces, scope the Trello token's permissions narrowly, and never commit API credentials to version control.
What it does
The Trello MCP Server connects Trello with AI assistants like Claude Desktop and GitHub Copilot Chat via the Model Context Protocol. It provides tools to list all open boards (list_boards), read a board's lists and cards (read_board), create lists and cards (create_list, create_card), move cards between lists (move_card), add comments (add_comment), archive cards or lists (archive_card, archive_list), rename lists or cards (update_list_name, update_card_name), and delete an entire board (delete_board). It also exposes boards as MCP resources (URI board:{boardId}) returning JSON of all lists and cards, so an assistant can read board state directly as context. Once configured, boards can be managed through natural language, e.g. "Create a new card called 'Review documentation' in the 'To Do' list" or "Move the 'Bug fix' card to the 'In Progress' list."
When to use - and when NOT to
Use it when you want an AI assistant to manage Trello boards on your behalf - reading task state, creating and organizing cards, or archiving completed work. Because delete_board permanently removes a board and its contents, and the server only requires the permissions granted via the Trello token, review any AI-issued delete or archive action before confirming it in a shared or production workspace, and scope the Trello token's permissions to what's actually needed. Per the project's own security notes, never commit API credentials to version control and rotate tokens regularly.
Inputs and outputs
Input is a natural-language request or direct tool call with board/list/card IDs and content (name, description, comment text). Output is the requested Trello state change (card created/moved/archived, board deleted, etc.) or, for read_board and the board:{boardId} resource, a JSON representation of the board's lists and cards.
How to install
Requires Node.js 20+ (or Docker) and Trello API credentials (API Key and Token from https://trello.com/app-key).
git clone https://github.com/lioarce01/trello-mcp-server.git
cd trello-mcp-server
npm install
npm run build
Register it in Claude Desktop's claude_desktop_config.json (or VS Code's settings.json for Copilot Chat) with the compiled entry point and credentials as environment variables (TRELLO_API_KEY, TRELLO_TOKEN, TRELLO_BASE_URL). A Docker option is also available: build with docker build -t trello-mcp-server . and run with docker run --rm -i --env-file .env trello-mcp-server; Docker containers run as a non-root user for security.
Who it's for
Individuals and teams who want an AI assistant to manage their Trello boards directly through chat - reading task state, creating and organizing cards, and handling routine board maintenance like archiving completed cards.
Source README
Trello MCP Server
A Model Context Protocol (MCP) server that connects Trello with AI assistants like Claude Desktop, GitHub Copilot Chat, and other MCP-compatible clients.
Features
- ๐ List all your Trello boards
- ๐ Read board contents (lists and cards)
- โ Create new cards
- ๐ Move cards between lists
- ๐ฌ Add comments to cards
- ๐๏ธ Archive cards
- ๐ Access boards as MCP resources
- ๐ณ Docker support for easy deployment
Prerequisites
- Node.js 20+ installed (for local development)
- Docker (for containerized deployment)
- A Trello account
- Trello API credentials (API Key and Token)
Installation
Option 1: Local Installation
- Clone this repository:
git clone https://github.com/lioarce01/trello-mcp-server.git
cd trello-mcp-server
- Install dependencies:
npm install
- Build the TypeScript code:
npm run build
Option 2: Docker Installation
- Clone this repository:
git clone https://github.com/lioarce01/trello-mcp-server.git
cd trello-mcp-server
- Build the Docker image:
docker build -t trello-mcp-server .
Getting Trello API Credentials
Get your API Key:
- Go to https://trello.com/app-key
- Copy your API Key
Get your Token:
- On the same page, click on "Token" link
- Authorize the application and copy your Token
Configuration
For Claude Desktop
Local Installation
Add the server configuration to your Claude Desktop config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/claude/claude_desktop_config.json
{
"mcp": {
"servers": {
"trello-mcp": {
"command": "node",
"args": ["absolute/path/to/the/project/dist/index.js"],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_TOKEN": "your_token",
"TRELLO_BASE_URL": "https://api.trello.com/1"
}
}
}
}
}
Docker Configuration
For Docker deployment, add this configuration:
{
"mcp": {
"servers": {
"trello-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"TRELLO_API_KEY=your_api_key",
"-e",
"TRELLO_TOKEN=your_token",
"-e",
"TRELLO_BASE_URL=https://api.trello.com/1",
"trello-mcp-server"
]
}
}
}
}
For VS Code with GitHub Copilot Chat
Local Installation
Add to your VS Code settings.json:
{
"mcp": {
"servers": {
"trello-mcp": {
"command": "node",
"args": ["absolute/path/to/the/project/dist/index.js"],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_TOKEN": "your_token",
"TRELLO_BASE_URL": "https://api.trello.com/1"
}
}
}
}
}
Docker Configuration
{
"mcp": {
"servers": {
"trello-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"TRELLO_API_KEY=your_api_key",
"-e",
"TRELLO_TOKEN=your_token",
"-e",
"TRELLO_BASE_URL=https://api.trello.com/1",
"trello-mcp-server"
]
}
}
}
}
Important:
- Replace
absolute/path/to/the/project/dist/index.jswith the actual absolute path to your compiled server file (local installation) - Replace
YOUR_TRELLO_API_KEYandYOUR_TRELLO_TOKENwith your actual Trello credentials
Docker Usage
Using Docker Run
# Build the image
docker build -t trello-mcp-server .
# Run with API key and token as arguments
docker run --rm -i --env-file .env trello-mcp-server
Local Testing
To test if your server works correctly:
- Build the project:
npm run build
- Run with credentials:
node dist/index.js
Docker Testing
- Build and run with Docker:
docker build -t trello-mcp-server .
docker run --rm -i --env-file .env trello-mcp-server
- You should see:
MCP server connected and ready.
Note: The server will wait for MCP client connections. To exit, press Ctrl+C.
Once configured, you can interact with your Trello boards through natural language:
List Boards
Show me all my Trello boards
Read Board Contents
What cards are in my "Project Management" board?
Create Cards
Create a new card called "Review documentation" in the "To Do" list
Move Cards
Move the "Bug fix" card to the "In Progress" list
Add Comments
Add a comment to the card saying "This needs urgent attention"
Archive Cards
Archive the completed card "Setup database"
Available Tools
| Tool | Description | Parameters |
|---|---|---|
list_boards |
List all open Trello boards | None |
read_board |
Read lists and cards from a specific board | boardId |
create_list |
Create a list | boardId, name |
create_card |
Create a new card in a specific list | listId, name, desc (optional) |
move_card |
Move a card to a different list | cardId, listId |
add_comment |
Add a comment to a card | cardId, text |
archive_card |
Archive a card | cardId |
archive_list |
Archive a list | listId |
delete_board |
Delete a board | boardId |
update_list_name |
Update a list name | listId, name |
update_card_name |
Update a card name | cardId, name |
Available Resources
The server exposes your Trello boards as MCP resources that can be read by AI assistants:
- Resource URI:
board:{boardId} - Content: JSON containing all lists and cards for the board
Development
Building
Local Development
npm run build
Docker Development
# Build Docker image
docker build -t trello-mcp-server .
Running in Development
Local Development
To run the server directly (for testing):
# With npm
npm run build
node dist/index.js
# With pnpm
pnpm run build
node dist/index.js
Docker Development
# Run with docker (pass credentials as arguments)
docker run --rm -i --env-file .env trello-mcp-server
Development Scripts
You can also create a development script in your package.json:
{
"scripts": {
"build": "tsc",
"start": "node dist/index.js",
"dev": "tsx ./src/index.ts",
"docker:build": "docker build -t trello-mcp-server .",
"docker:run": "docker run --rm -i --env-file .env trello-mcp-server"
}
}
Troubleshooting
Server Not Connecting
- Check credentials: Make sure you're passing API Key and Token as arguments
- Verify file path: Ensure the path in your MCP configuration is correct (local installation)
- Build first: Always run
npm run buildordocker buildbefore testing - Test standalone: Try running the server independently first
- Restart client: Restart your MCP client (Claude Desktop/VS Code) after config changes
Docker-Specific Issues
- Image not found: Make sure you've built the Docker image first with
docker build -t trello-mcp-server . - Arguments not passed: Ensure API key and token are passed as arguments after the image name
- Permissions: Check that Docker has the necessary permissions to run containers
Invalid Credentials Error
- Double-check your Trello API Key and Token
- Ensure the token has the necessary permissions
- Try regenerating your token if it's expired
- Verify credentials are properly passed as arguments
Tools Not Working
- Verify the board/card/list IDs are correct
- Check that you have write permissions to the Trello board
- Look at the console logs for detailed error messages
Security Notes
- Never commit your API credentials to version control
- Store credentials securely and rotate them regularly
- Use
.envfiles and add them to.gitignore - The server only requires the permissions you grant via the Trello token
- Consider using environment variables for credentials in production
- Docker containers run with non-root user for security
FAQ
Common questions
Discussion
Questions & comments ยท 0
Sign In Sign in to leave a comment.