Trello Knowledge MCP Server
An MCP server that utilizes Trello as a knowledge base for storing, searching, and retrieving code snippets and notes. It enables full CRUD operations and organized categorization of information using Trello boards and labels.
README
Trello MCP Server
An MCP (Model Context Protocol) server that uses Trello as a knowledge base for storing and retrieving code snippets, notes, and other information.
Attention(!!)
Claude wrote this. I didnt verify line by line what it wrote. So be aware when using this and do your own review. I provide this repo as is and will not be responsible for any damages this causes.
Features
- Store code snippets and notes as Trello cards
- Search across card titles, descriptions, and labels
- Organize knowledge by boards and lists
- Tag-based categorization using Trello labels
- Full CRUD operations on your knowledge base
Setup
Prerequisites: Make sure you have direnv installed for environment variable management.
-
Get Trello API credentials:
- First, create a Power-Up at https://trello.com/power-ups/admin (required for API access)
- Go to your Power-Up's "API Key" tab and generate a new API key
- Generate a Token by clicking the Token link (its hidden in the text)
- Copy both your API Key and Token
-
Create a Knowledge Board:
- Create a new Trello board for your knowledge base
- Create lists like "Code Snippets", "Configuration", "Notes", etc.
- Copy the board ID from the URL
-
Configure environment with direnv:
# Edit .envrc with your Trello credentials # Make sure direnv is installed and allowed for this directory direnv allow -
Install and run:
npm install npm start -
Configure Claude Desktop: Add this to your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:%APPDATA%\Claude\claude_desktop_config.jsonLinux:~/.config/Claude/claude_desktop_config.json{ "mcpServers": { "trello-knowledge": { "command": "node", "args": ["src/index.js"], "cwd": "/path/to/your/trello-mcp-server", "env": { "TRELLO_API_KEY": "your_api_key_here", "TRELLO_TOKEN": "your_token_here", "TRELLO_KNOWLEDGE_BOARD_ID": "your_board_id_here" } } } }Windows PowerShell (if Node.js isn't in PATH):
{ "mcpServers": { "trello-knowledge": { "command": "C:\\Program Files\\nodejs\\node.exe", "args": ["C:\\Users\\YourUsername\\path\\to\\trello-mcp-server\\src\\index.js"], "env": { "TRELLO_API_KEY": "your_api_key_here", "TRELLO_TOKEN": "your_token_here", "TRELLO_KNOWLEDGE_BOARD_ID": "your_board_id_here" } } } }Alternative with direnv (if you want Claude Desktop to inherit your shell environment):
{ "mcpServers": { "trello-knowledge": { "command": "bash", "args": ["-c", "cd /path/to/your/trello-mcp-server && eval \"$(direnv export bash)\" && node src/index.js"], "cwd": "/path/to/your/trello-mcp-server" } } } -
Restart Claude Desktop for the changes to take effect.
Usage
Once connected to Claude Desktop, you can:
- Store knowledge: "Remember that in Symfony, to prettify JSON responses, I use..."
- Retrieve knowledge: "How did I handle JSON responses in Symfony?"
- Search: "Show me all my Docker-related snippets"
- Organize: Cards are automatically tagged and categorized
MCP Tools Available
store_knowledge- Save a new piece of informationsearch_knowledge- Find existing informationget_knowledge- Retrieve specific knowledge by IDlist_topics- Show all available topics/categories
License
This project is licensed under the MIT License - see the LICENSE file for details.
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。