Trello MCP Server - Optimized
A high-performance MCP server for Trello integration with 97% token reduction through intelligent response optimization, enabling efficient board, card, and list management.
README
Trello MCP Server - Optimized
A high-performance Model Context Protocol (MCP) server for Trello integration with 97% token reduction through intelligent response optimization.
Installation
Option 1: Quick Setup (Recommended)
# Download and run the setup script
curl -O https://raw.githubusercontent.com/Deepankar1993/trello-mcp-server-optimize/master/install.sh && chmod +x install.sh && ./install.sh
This will:
- Install the package globally
- Configure your Trello API credentials
- Set up Claude Desktop/CLI automatically
Option 2: Manual Installation
# Install globally
npm install -g @cyberdeep/trello-mcp-server-optimize
After installation, configure Claude using one of these methods:
Claude CLI
claude mcp add-json trello-mcp-server --scope user '{
"command": "trello-mcp-optimize",
"args": [],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_TOKEN": "your_token"
}
}'
Claude Desktop
Manually add to your config file:
{
"mcpServers": {
"trello-mcp-server": {
"command": "trello-mcp-optimize",
"args": [],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_TOKEN": "your_token"
}
}
}
}
Configuration
Get Trello API Credentials
- Visit Trello Power-Ups Admin
- Click "New" and create a Power-Up
- Generate an API Key and Token
Alternative: Using NPX (No Install Required)
You can also use npx directly without installing:
Claude Desktop Config
Add to your config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/claude/claude_desktop_config.json
{
"mcpServers": {
"trello-mcp-server": {
"command": "npx",
"args": ["-y", "@cyberdeep/trello-mcp-server-optimize"],
"env": {
"TRELLO_API_KEY": "your_api_key",
"TRELLO_TOKEN": "your_token"
}
}
}
}
Features
- 🚀 97% Token Reduction - Intelligent response filtering and summarization
- 📊 Smart Defaults - Automatic optimization based on operation type
- ⚡ High Performance - In-memory caching with smart TTLs
- 🔧 Full Trello API Coverage - 75+ operations for boards, cards, lists, and more
- 📦 Zero Configuration - Works out of the box with sensible defaults
- 🔄 100% Backward Compatible - Drop-in replacement for existing integrations
Usage Examples
// Get your boards (automatically optimized)
"Show me my Trello boards"
// Create a new card
"Create a card called 'Review documentation' in my To Do list"
// Get cards with optimization
"Get the first 10 urgent cards from my project board"
// Summarize large datasets
"Give me a summary of all cards in my backlog"
Performance Comparison
| Operation | Standard API | Optimized | Reduction |
|---|---|---|---|
| List Boards | ~800 tokens | ~80 tokens | 90% |
| Get Card Details | ~1200 tokens | ~120 tokens | 90% |
| List Cards (100+) | ~5000 tokens | ~150 tokens | 97% |
Available Tools
Board Operations
get_boards- List all boardsget_board- Get board detailscreate_board- Create new boardupdate_board- Update boarddelete_board- Delete boardget_board_lists- Get lists on boardget_board_members- Get board membersget_board_labels- Get board labels
Card Operations
get_card- Get card detailscreate_card- Create new cardupdate_card- Update carddelete_card- Delete cardmove_card_to_list- Move cardadd_comment- Add comment to cardadd_member- Assign member to cardset_due_date- Set card due date
List Operations
get_list- Get list detailscreate_list- Create new listupdate_list- Update listarchive_list- Archive listget_cards_in_list- Get cards in listmove_all_cards- Move all cards
Advanced Features
Optimization Levels
// Minimal - Essential fields only (90% reduction)
{ tool: "get_boards", arguments: { detailLevel: "minimal" } }
// Standard - Common fields (default)
{ tool: "get_card", arguments: { cardId: "123" } }
// Detailed - Most fields
{ tool: "get_board", arguments: { boardId: "456", detailLevel: "detailed" } }
// Full - Complete response
{ tool: "get_card", arguments: { cardId: "789", detailLevel: "full" } }
Array Optimization
// Limit results
{ tool: "get_cards_in_list", arguments: { listId: "abc", maxItems: 10 } }
// Summarize large datasets (returns 5 items by default with statistics)
{ tool: "get_boards", arguments: { summarize: true } }
// Summarize with custom limit (returns 20 items with statistics)
{ tool: "get_cards_in_list", arguments: { listId: "abc", summarize: true, maxItems: 20 } }
Note on summarize parameter:
- When
summarize: trueis used, the response includes only the first 5 items by default along with summary statistics - Use
maxItemstogether withsummarize: trueto override the default 5-item limit - Without
summarizeor withsummarize: false, all items are returned (unless limited bymaxItems)
Development
# Clone repository
git clone https://github.com/Deepankar1993/trello-mcp-server-optimize.git
cd trello-mcp-server-optimize
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
Environment Variables
Required:
TRELLO_API_KEY- Your Trello API keyTRELLO_TOKEN- Your Trello API token
Optional:
ENABLE_RESPONSE_OPTIMIZATION- Enable/disable optimization (default:true)DEFAULT_OPTIMIZATION_LEVEL- Default optimization level (default:smart)ENABLE_CACHING- Enable response caching (default:true)
Troubleshooting
Connection Issues
If you see "Status: ✘ failed" in Claude:
- Verify your API credentials are correct
- Restart Claude Desktop completely
- Check the logs for errors
Common Issues
- NPX not working: Use global install instead:
npm install -g @cyberdeep/trello-mcp-server-optimize - Permission errors: Use
sudo npm install -gor configure npm to use a different directory - Server not found: Make sure the package is installed globally
Documentation
Contributing
Contributions are welcome! Please read our contributing guidelines and submit pull requests to our repository.
License
MIT © Deepankar
Support
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。