KM

kunwarvivek/mcp-github-project-manager

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

104 stars 28 forks 质量 89 趋势 35MIT

kunwarvivek/mcp-github-project-manager 是从 https://github.com/kunwarvivek/mcp-github-project-manager. 导入的 MCP 服务器候选

概览

kunwarvivek/mcp-github-project-manager 是从 https://github.com/kunwarvivek/mcp-github-project-manager. 导入的 MCP 服务器候选

概述(AI 翻译)

AI编码代理的代理任务基层。 一台MCP服务器,将GitHub Projects v2转变为完全自主的项目管理平台——AI代理自分配工作、跟踪进度、相互审查并交付代码,所有这些都由GitHub原生存储支持。

用例:你有AI代理(Claude Code、Codex、Cursor、Windsurf、Roo)。他们需要一个任务骨干。就是这个。

概述

该MCP服务器实现了模型上下文协议,为GitHub Projects v2提供了完整的代理项目管理层。AI代理注册、自分配任务、通过心跳协调、提交工作产品以供审核,并在代币预算内操作——所有这些都通过20个复合工具,共暴露169个动作。人类项目经理可以获得AI驱动的PRD生成、冲刺规划、问题分流和路线图创建。所有内容都由GitHub原生存储(问题、项目字段、评论)支持——无需外部基础设施。

为什么会有这样的存在

AI编码代理强大但无状态——它们不知道下一步该做什么,无法与其他代理协调,也没有持久的任务记忆。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

MCP GitHub Project Manager

The task substrate for AI coding agents. An MCP server that turns GitHub Projects v2 into an agentic project-management layer: agents register, self-assign work, heartbeat, submit work products for review, and spend against token budgets — through 20 compound tools exposing 169 actions, backed entirely by GitHub-native storage. No database, no Redis, no external infra.

You bring the agents (Claude Code, Codex, Cursor, Windsurf, Roo, OpenCode, any MCP client). This is the backbone that tells them what to work on and keeps them from colliding.

Surface Detail
Tools 20 compound tools, 169 actions, action-routed
Resources 6 read-only GitHub-backed views
Prompts 6 reusable AI templates
Transport MCP v2 over stdio (webhook/SSE optional)
Storage GitHub issues, project fields, comments — no external infra
Runtime Node >= 22.12.0 · MIT license

Why this exists

  • Agents need a work queue, not a chat window. agent_work / agent_manage give agents atomic task checkout, heartbeats, and a review loop instead of “go figure it out.”
  • Budgets must be enforced somewhere the agent cannot skip. Each agent has a token budget with warning thresholds and a hard stop; the server debits itself, and record_usage covers the agent’s own runtime spend.
  • AI plans are worthless if they never become issues. ai_generate runs idea → PRD → tasks → materialized GitHub issues, grouped into milestones and sprints.
  • Tool lists are a context tax. 20 tools instead of 169 keeps the schema small; discover_tools expands any domain or action on demand.
  • State should live where the work already is. The agent registry is a file on a dedicated branch (compare-and-swap writes), task claims are project fields, work products are issue comments — no new infrastructure to operate.

Quick start

Requires Node.js >= 22.12.0 (Node 24 recommended).

# 1. Install (global, or use npx / pnpm dlx / docker compose — see below)
npm install -g mcp-github-project-manager

# 2. Configure (a working `gh auth login` means you can skip GITHUB_TOKEN)
export GITHUB_TOKEN="ghp_..."
export GITHUB_OWNER="your-org-or-user"
export GITHUB_REPO="your-repo"
在 GitHub 查看完整 README

安装

npx -y mcp-github-project-manager
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "github-project-manager": { "command": "npx", "args": ["-y", "mcp-github-project-manager"], "env": { "GITHUB_TOKEN": "ghp_...", "GITHUB_OWNER": "your-org-or-user", "GITHUB_REPO": "your-repo" } } } }