Trello MCP Server
Enables Claude to manage Trello boards, lists, cards, labels, and checklists via the Trello REST API, allowing natural language task management.
README
Trello MCP Server
A Model Context Protocol (MCP) server for the Trello REST API. Connects Claude Desktop to your Trello workspace, giving Claude tools to manage boards, lists, cards, labels, and checklists.
Features
- Boards — list, get, and create boards
- Lists — list, create, and update lists
- Cards — list, get, create, update, and delete cards (including moving between lists and setting due dates)
- Labels — list, create, add to cards, and remove from cards
- Checklists — get, create, add items, and check/uncheck items
Prerequisites
- Node.js v18 or higher
- A Trello account
- Claude Desktop
Setup
1. Clone the repo
git clone https://github.com/ChrisLochhead/Trello-MCP-Server.git
cd Trello-MCP-Server
2. Install dependencies and build
npm install
npm run build
3. Get your Trello API credentials
- Go to https://trello.com/power-ups/admin
- Create a new Power-Up (name it anything — e.g. "My MCP App")
- Navigate to the API Key tab and click Generate a new API Key — copy the key
- On the same page, click the Token link, authorize, and copy the token from the resulting page
4. Configure Claude Desktop
Open your Claude Desktop config file:
- Windows:
C:\Users\<YourUsername>\AppData\Local\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the following inside the top-level JSON object (not inside "preferences"):
"mcpServers": {
"trello": {
"command": "C:\\Program Files\\nodejs\\node.exe",
"args": ["C:\\path\\to\\Trello-MCP-Server\\dist\\index.js"],
"env": {
"TRELLO_API_KEY": "your_api_key_here",
"TRELLO_API_TOKEN": "your_token_here"
}
}
}
Note for Windows users: use the full path to
node.exe(find it by runningwhere nodein Command Prompt). Use double backslashes in the path.
5. Restart Claude Desktop
After saving the config, restart Claude Desktop. In a new conversation, you can test it by asking:
"List my Trello boards"
Available Tools
| Tool | Description |
|---|---|
trello_list_boards |
List all boards for the authenticated user |
trello_get_board |
Get a board's details and lists |
trello_create_board |
Create a new board |
trello_list_lists |
Get all lists on a board |
trello_create_list |
Create a new list on a board |
trello_update_list |
Rename, archive, or reposition a list |
trello_list_cards |
List cards on a board or list |
trello_get_card |
Get full card details |
trello_create_card |
Create a new card |
trello_update_card |
Update a card (name, description, due date, list, etc.) |
trello_delete_card |
Permanently delete a card |
trello_list_labels |
Get all labels on a board |
trello_create_label |
Create a new label |
trello_add_label_to_card |
Add a label to a card |
trello_remove_label_from_card |
Remove a label from a card |
trello_get_card_checklists |
Get all checklists on a card |
trello_create_checklist |
Add a checklist to a card |
trello_add_checklist_item |
Add an item to a checklist |
trello_update_checklist_item |
Check/uncheck or rename a checklist item |
Development
npm run dev # Run with auto-reload (tsx watch)
npm run build # Compile TypeScript to dist/
npm run clean # Remove dist/
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。