Honu Context-Powered Todo MCP Server

Honu Context-Powered Todo MCP Server

Enables context-powered task management on Trello boards, automatically creating detailed sprint tasks with acceptance criteria and QA steps using AI.

Category
访问服务器

README

Honu Context-Powered Todo MCP

This repository provides an MCP (Model Context Protocol) server that integrates with Trello to enable context-powered task boards. It extends your agent with powerful tools to automatically manage Trello boards, create context-aware sprint tasks, and maintain detailed business context right within your project management system.

Requirements

Ensure you have the following installed before proceeding:

  • Python and Poetry: Used to manage the Python environment and dependencies for the MCP server.
  • NodeJS and npx: Required for executing specific Javascript-based MCP tools or utilities if needed.
  • Trello API Key and API Token: You will need these to authenticate the server with Trello. (This guide from Trello can help you generate them).

Installation and Setup

  1. Clone this repository to your local machine.
  2. Install dependencies by running poetry install inside the project folder.
  3. Configure your agent by adding the following to your agent's MCP configuration file (make sure to replace /path/to/repository, <YOUR TRELLO API KEY>, and <YOUR TRELLO API TOKEN> with your actual values):
{
  "mcpServers": {
    "context_todo_board": {
      "command": "poetry",
      "args": [
        "-C",
        "/path/to/repository",
        "run", 
        "python", 
        "honu_context_powered_todo_mcp/server.py"
      ],
      "env": {
        "TRELLO_API_KEY": "<YOUR TRELLO API KEY>",
        "TRELLO_API_TOKEN": "<YOUR TRELLO API TOKEN>"
      }
    }
  }
}

Note: This server also securely proxies the Trello MCP Server from delorenj, giving you full access to standard Trello operations alongside context-powered enhancements.

Using Skills

This project includes special Skills that act as specialized workflows and instructions for the agent to perform complex, domain-specific tasks.

Skills are located in the .agent/skills/ directory (or can be packaged as .skill files). To use them, simply ask the agent to perform the task described by the skill. The agent will automatically recognize your intent and follow the skill's specific instructions.

Included Skills

  1. Trello Card Creator (trello-card-creator)

    • What it does: A workflow for creating highly detailed, developer-ready Trello cards for sprint tasks. It acts like a Senior Full Stack Developer, automatically fetching project context (MVP definitions, user journeys) and expanding tasks into actionable JIRA-like tickets completely fleshed out with Acceptance Criteria and prescriptive QA validation steps.
    • How to use: Ask the agent to "detail the tasks for our current sprint" or "create Trello cards for the MVP phase". The agent will leverage this skill to gather context proactively, prompt you for review if needed, and create the cards directly in Trello using MCP tools.
  2. Skill Creator (skill-creator)

    • What it does: A meta-skill that guides the agent in properly creating new skills or updating existing ones. It ensures that any new capabilities you want to add follow the best practices for progressive disclosure, resource structuring, and concise prompting.
    • How to use: Ask the agent to "create a new skill for [your specific task] taking into account the skill creator guide" or "update the existing XYZ skill." The agent will use this skill to correctly design, initialize, and test the custom workflow.

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