trello-mcp-server
Integrates Trello with Claude Code for advanced project planning and task management, featuring intelligent task analysis, automatic board setup, and natural language due dates.
README
Trello MCP Server for Claude Code
A Model Context Protocol (MCP) server that integrates Trello with Claude Code, providing advanced project planning and task management capabilities with intelligent task analysis.
Features
🎯 Core Task Management
- Create, read, update, and delete tasks across Trello boards and lists
- Automatic board setup with standard lists (To Do, In Progress, Done)
- Priority management with visual indicators
- Due date handling with natural language support ("tomorrow", "next week")
- Status tracking that maps to Trello list positions
🧠 Intelligent Task Analysis
- Complexity assessment (simple/moderate/complex) based on content analysis
- Vague task detection using natural language processing
- Automatic task splitting for overly complex tasks
- Clarity validation with generated clarifying questions
- Board-wide analysis with focused reporting
🔧 Advanced Features
- Batch operations for efficient task management
- Natural language due dates (today, tomorrow, next week)
- Priority-based task organization
- Comprehensive task filtering by status, priority, or due date
- Real-time task intelligence during creation
Installation
-
Clone and setup the project:
git clone <repository-url> cd trello-mcp-server npm install -
Configure Trello API credentials:
- Copy
.env.exampleto.env - Get your Trello API key from: https://trello.com/app-key
- Generate an API token by visiting: https://trello.com/1/authorize?expiration=never&scope=read,write&response_type=token&name=Claude%20Code%20MCP&key=YOUR_API_KEY
- Update
.envwith your credentials:TRELLO_API_KEY=your_api_key_here TRELLO_API_TOKEN=your_api_token_here DEFAULT_TRELLO_BOARD_ID=optional_default_board_id
- Copy
-
Build the server:
npm run build
Claude Code Integration
Project-Level Configuration (Recommended)
Create .mcp.json in your project root:
{
"mcpServers": {
"trello": {
"command": "node",
"args": ["/path/to/trello-mcp-server/build/index.js"],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_API_TOKEN": "your_api_token",
"DEFAULT_TRELLO_BOARD_ID": "your_default_board_id"
}
}
}
}
Global Configuration
Add to your Claude Code configuration:
claude mcp add-json '{
"command": "node",
"args": ["/path/to/trello-mcp-server/build/index.js"],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_API_TOKEN": "your_api_token"
}
}'
Usage Examples
Basic Task Management
// List available boards
await trello_list_boards();
// Setup a board with default lists
await trello_setup_board({ boardId: "board_id" });
// Create a task with intelligence
await trello_create_task({
boardId: "board_id",
title: "Implement user authentication",
description: "Create login/logout functionality with JWT tokens",
priority: "high",
dueDate: "next week"
});
// Update task status (automatically moves between lists)
await trello_update_task({
cardId: "card_id",
status: "in_progress"
});
Intelligent Task Analysis
// Analyze entire board for improvements
await trello_analyze_board({
boardId: "board_id",
focusArea: "vague" // or "complex", "overdue", "all"
});
// Get clarifying questions for a vague task
await trello_clarify_task({
cardId: "card_id"
});
// Split a complex task into smaller ones
await trello_split_task({
cardId: "card_id",
autoCreate: true // Automatically create the suggested splits
});
Advanced Filtering
// Get tasks by status
await trello_get_tasks({
boardId: "board_id",
status: "in_progress"
});
// Get tasks from specific list
await trello_get_tasks({
boardId: "board_id",
listName: "To Do"
});
Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
trello_list_boards |
List all accessible boards | - |
trello_get_board |
Get board details with statistics | boardId |
trello_create_task |
Create task with intelligence | boardId, title, description, priority, dueDate |
trello_update_task |
Update task or change status | cardId, title, description, status |
trello_analyze_board |
Analyze board for improvements | boardId, focusArea |
trello_split_task |
Split complex tasks | cardId, autoCreate |
trello_clarify_task |
Generate clarifying questions | cardId |
trello_get_tasks |
Filter and retrieve tasks | boardId, listName, status |
trello_setup_board |
Setup default task management lists | boardId |
Task Intelligence Features
Complexity Detection
The system automatically identifies task complexity based on:
- Content length and sentence structure
- Technical keywords (API, database, authentication, etc.)
- Multiple action verbs indicating compound tasks
- Implementation complexity indicators
Vague Task Detection
Automatically flags tasks containing:
- Unclear language ("somehow", "figure out", "handle", etc.)
- Missing acceptance criteria
- Ambiguous requirements
- Incomplete implementation details
Automatic Task Splitting
Intelligently suggests task splits based on:
- Natural language conjunctions ("and", "or")
- Comma-separated requirements
- Complex implementation patterns
- Standard development phases (planning, implementation, testing)
Development
Running in Development Mode
npm run dev # Watches for changes and rebuilds
Testing with MCP Inspector
npx @modelcontextprotocol/inspector build/index.js
Environment Variables
TRELLO_API_KEY- Your Trello API key (required)TRELLO_API_TOKEN- Your Trello API token (required)DEFAULT_TRELLO_BOARD_ID- Default board for operations (optional)
Architecture
Components
- TrelloClient: Core API wrapper with full CRUD operations
- TaskAnalyzer: Natural language processing for task intelligence
- MCP Server: Protocol implementation with comprehensive tool handlers
Data Flow
Claude Code → MCP Client → Trello MCP Server → Trello REST API → Trello Boards
Task State Mapping
- Pending → "To Do" list
- In Progress → "In Progress" list
- Completed → "Done" list
Contributing
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Submit a pull request
License
MIT License - see LICENSE file for details.
Support
For issues and feature requests, please open an issue on GitHub or refer to the Trello API documentation for API-related questions.
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。