Trello MCP Server on Cloudflare Workers

Trello MCP Server on Cloudflare Workers

Enables comprehensive Trello integration via MCP, supporting boards, lists, cards, comments, labels, members, checklists, search, and attachments, deployed on Cloudflare Workers.

Category
访问服务器

README

Trello MCP Server on Cloudflare Workers

A Model Context Protocol (MCP) server that provides comprehensive Trello integration, deployed on Cloudflare Workers with secure authentication.

🚀 Live Deployment

Server URL: https://trello-mcp-cloudflare-v2.matthias-51d.workers.dev

Endpoints:

  • SSE Transport: /sse (Server-Sent Events for persistent connections)
  • HTTP Transport: /mcp (JSON-RPC over HTTP for simple requests)

🔧 Features

Trello Operations Supported:

  • Boards: List, get, create boards
  • Lists: Get lists, create lists
  • Cards: Get, create, update, move, delete cards
  • Comments: Add and retrieve card comments
  • Labels: Manage board labels and card labels
  • Members: Manage board members and card assignments
  • Checklists: Create checklists and manage checklist items
  • Search: Search cards across your Trello workspace
  • Attachments: Attach URLs to cards

🔐 Authentication

The server uses secure authentication with environment variables:

Required Environment Variables:

  • TRELLO_API_KEY: Your Trello API key (Get it here)
  • TRELLO_TOKEN: Your Trello token (Generate here)
  • SHARED_SECRET: Shared secret for MCP authentication

Authentication Methods:

  1. URL Parameter: ?secret=your_shared_secret
  2. Authorization Header: Authorization: Bearer your_shared_secret

📦 Setup & Deployment

Prerequisites:

  • Node.js 18+
  • Cloudflare account
  • Trello API credentials

Local Development:

# Clone the repository
git clone https://github.com/M-Kampmann/trello-mcp-cloudflare.git
cd trello-mcp-cloudflare

# Install dependencies
npm install

# Copy environment variables template
cp .dev.vars.example .dev.vars

# Edit .dev.vars with your actual credentials
# TRELLO_API_KEY=your_api_key
# TRELLO_TOKEN=your_token
# SHARED_SECRET=your_secret

# Start local development server
npm run dev

Deploy to Cloudflare:

# Set production secrets
wrangler secret put TRELLO_API_KEY
wrangler secret put TRELLO_TOKEN
wrangler secret put SHARED_SECRET

# Deploy to Cloudflare Workers
npm run deploy

🔌 Usage Examples

Test Authentication:

# Test with correct secret (should work)
curl "https://trello-mcp-cloudflare-v2.matthias-51d.workers.dev/sse?secret=your_secret"

# Test with wrong secret (should return 401)
curl "https://trello-mcp-cloudflare-v2.matthias-51d.workers.dev/sse?secret=wrong_secret"

MCP Client Integration:

# Using mcp-remote proxy
npx mcp-remote https://trello-mcp-cloudflare-v2.matthias-51d.workers.dev/sse?secret=your_secret

🖥️ Claude Desktop Integration

Add to your Claude Desktop configuration (claude_desktop_config.json):

{
  "mcpServers": {
    "trello": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://trello-mcp-cloudflare-v2.matthias-51d.workers.dev/sse?secret=your_shared_secret"
      ]
    }
  }
}

🛠️ Development

Project Structure:

├── src/
│   └── index.ts          # Main MCP server implementation
├── wrangler.toml         # Cloudflare Workers configuration
├── package.json          # Dependencies and scripts
├── .dev.vars.example     # Environment variables template
└── README.md            # This file

Available Tools:

  • listBoards - Get all accessible boards
  • getBoard - Get specific board details
  • createBoard - Create a new board
  • getLists - Get lists from a board
  • createList - Create a new list
  • getCards - Get cards from a list
  • getBoardCards - Get all cards from a board
  • getCard - Get specific card details
  • createCard - Create a new card
  • updateCard - Update card properties
  • moveCard - Move card between lists
  • deleteCard - Delete a card
  • addComment - Add comment to card
  • getComments - Get card comments
  • addLabel - Add label to card
  • removeLabel - Remove label from card
  • getBoardLabels - Get board labels
  • createLabel - Create new label
  • addMemberToCard - Assign member to card
  • removeMemberFromCard - Remove member from card
  • getBoardMembers - Get board members
  • createChecklist - Create checklist on card
  • addChecklistItem - Add item to checklist
  • getCardChecklists - Get card checklists
  • searchCards - Search cards by query
  • attachUrlToCard - Attach URL to card
  • getCurrentUser - Get current user info
  • archiveListCards - Archive all cards in list

🔒 Security

  • All API credentials are stored as Cloudflare Workers secrets
  • Authentication required for all endpoints
  • CORS properly configured for web clients
  • No sensitive data exposed in logs

📝 License

MIT License - see LICENSE file for details

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Test thoroughly
  5. Submit a pull request

🐛 Troubleshooting

Common Issues:

Authentication Errors:

  • Verify your SHARED_SECRET is set correctly
  • Check that Trello API credentials are valid
  • Ensure you're using the correct URL parameter format

Connection Issues:

  • Verify the server URL is accessible
  • Check that CORS headers are properly set
  • Test with curl first before using MCP clients

Deployment Issues:

  • Ensure all secrets are set in Cloudflare Workers
  • Check wrangler.toml configuration
  • Verify Node.js compatibility settings

For more help, check the Cloudflare Workers documentation or MCP specification.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选