原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

Quarterdeck

作者:shannonbay版本 0.32.0i★ 43i在你的电脑上运行代码仓库 ↗
注册名称io.github.shannonbay/quarterdeck

安装方法

能做什么

Persistent goals for Claude: standing objectives with items, memory and approvals.

作者提供的原文

  • 连接方式 在你的电脑上运行
  • 账号或密钥 无需密钥
  • 分类 搜索与 AI 记忆

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

作者:google-research★ 35,6511 个 skill

Skill · 操作手册

Shadowbroker

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…

作者:BigBodyCobain★ 11,6101 个 skill

Skill · 操作手册

google-maps-scraper

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

作者:gosom★ 8,2781 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度20/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分32/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 3/3 项检查 · 在你的电脑上运行

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude,但需要先准备

不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

  1. 下载开发者的安装文件

    下载作者的 .mcpb 文件

    .mcpb 文件直接来自开发者,我们没有修改

  2. 双击文件,然后在电脑版 Claude 应用中点击 Install

  3. 试一试

    用 Quarterdeck 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Quarterdeck,或回答中出现 Quarterdeck 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

ChatGPT 暂时无法连接 Quarterdeck

Quarterdeck 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器

你可以改用这些方式

A · 使用能连接 Quarterdeck 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

B · 搜索与 AI 记忆 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Quarterdeck

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Quarterdeck 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

Cursor 暂时无法连接 Quarterdeck

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Quarterdeck 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

VS Code 暂时无法连接 Quarterdeck

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Quarterdeck 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Quarterdeck 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
许可证i
Apache-2.0
连接方式
在你的电脑上运行
最新版本i
0.32.0
发布到注册中心i
2026年11月21日
代码最后更新i
2026年11月21日
作者
shannonbay
软件包
mcpb: …/quarterdeck-0.32.0.mcpb
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月21日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 shannonbay 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于今天

  • ✓ 通过

    有许可证

    使用 Apache-2.0

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

已公开的漏洞(OSV.dev)

未检查:只能检查标明版本的 npm 和 PyPI 包

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/shannonbay-quarterdeck.svg)](https://mcp.popnx.com/en/servers/shannonbay-quarterdeck)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 6559 个服务器的 96%
  • 发布到注册中心的时间比此分类中其他 6559 个服务器的 99% 更新
  • 基础检查结果等于或优于此分类中其他 6559 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Quarterdeck 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于今天,最新版本(0.32.0)于今天进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。

有什么可以替代它?

同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

作者:every-app广泛使用★ 2.8万7天前更新

在云端运行✓ everyapp.com

Exa

Official Exa MCP for web search, content fetching, and multi-step research.

作者:exa-labs广泛使用★ 5249昨天更新

在云端运行✓ 服务方 · exa.aiPopNx 团队已实际试用

Microsoft Learn MCP

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

作者:MicrosoftDocs广泛使用★ 200212个月前更新

在云端运行✓ 服务方 · microsoft.comPopNx 团队已实际试用

Docs

Search and read Empryo's documentation. Read-only, no auth, no local access.

作者:proxysoul正在增长★ 16293个月前更新

在云端运行✓ empryo.com
与相似项目对比
本项
Quarterdeck
OpenSEOExaMicrosoft Learn MCPDocsCOTAL actions (cotal.ai)
运行位置需要安装在电脑上在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否是是是否否
基础检查3/35/52/44/44/44/4
许可证Apache-2.0MITMITCC-BY-4.0NOASSERTIONApache-2.0
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Quarterdeck

Quarterdeck keeps Claude on top of things for you.

One prompt, /goal-new Sell my birdcage on Facebook Marketplace, and it sold for the asking price the next day. Claude wrote and posted the listing, answered five buyers and lined up the pick-up, and every message waited for my OK first.

*How the sale went · the whole sale on video (2 min) · an agent fixing issues on this repo (80 s). Buyers' names are changed and older chats blurred; the opening was re-created with a cleaner prompt, and the rest is screenshots from the real sale.*

Install it in two commands (you need Claude Code and Node.js 22.13+), then type /goal-new in Claude Code:

claude plugin marketplace add shannonbay/Quarterdeck#release

claude plugin install quarterdeck-goals@quarterdeck --scope user

More in the Quickstart.

What it is

It's a Claude Code plugin that turns Claude into a personal assistant: it keeps looking after the things you hand it, asks before it does anything you haven't allowed, and remembers what you decided.

You give it goals: "sell my birdcage on facebook marketplace", "fix new issues on my repo", "find me the three best new job ads each week", "turn NZ$200 into more by flipping Marketplace bargains", "clear old installers out of Downloads". Each goal runs on its own schedule in the background of your Claude Code session, on your Claude plan. When it wants to act, it proposes, and you approve or reject from the Goals pane beside your chat, or from your phone.

The idea behind it: persistent intent may matter more than persistent memory. Instead of prompt → act, a goal is an action cycle that keeps going, punctuated only by your approvals and the occasional question.

What it's like

  • It asks first. A buyer offers $30 for your $50 birdcage, and the reply countering at $40 waits under Needs you until you approve it. Nothing goes to a buyer before that. Rejected with "too formal"? That feedback becomes memory, and later runs follow it.
  • It reaches you when you're away. With Remote Control connected, a new proposal or question pushes to the Claude app on your phone. Reply "approve" and it's done.
  • It asks when it's stuck. When a run needs something only you can give (your lowest price, when buyers can pick up), it asks under Needs you instead of guessing, and carries on with your answer.
  • It earns trust one kind of action at a time. Each kind of action (message a buyer, buy, delete a file) is *off*, *propose* or *auto*. After 10 approvals in a row, the pane offers to switch that kind to auto.
  • It remembers. Each goal keeps its own memory, its open items (never assessing the same listing twice) and its run history, outside any one conversation.
  • It works on Quarterdeck too. PR #30, watches that fire when a state changes, was written and opened by a Quarterdeck goal from issue #29; I tested it live and merged it. How that works.
  • You see what it costs. Each run shows its tokens and time, e.g. · 48k tokens · 2m.

*A friend's goal selling his old audio gear stops to ask for condition notes and his floor price instead of guessing.*

Start with /goal-new: pick a ready-made goal (maintain my repo, which sets up all the GitHub goals below at once, unsubscribe from mailing lists, a daily news digest, a weekly job scan with your CV, tidy Downloads, inbox triage, keep your GitHub profile current, fix failing CI, triage new GitHub issues, refine new GitHub issues, work on new GitHub issues, review pull requests, flip items on Facebook Marketplace) or type your own. Schedules can be plain words: "30d", "weekdays at 9", "the first of every month".

Example: selling a birdcage

It started with one prompt: /goal-new Sell my as-new (unused) birdcage on Facebook Marketplace. I live in Tawa, Wellington. The photos are the two newest pictures in my Pictures folder. Price $50, pick-up only. The GIF at the top shows it.

  1. The first run found the two photos, wrote the listing (dimensions in centimetres, category, condition) and proposed posting it. Nothing went up until I approved it in the Goals pane.
  2. Approved, the next run filled in Facebook's form through Claude in Chrome, published the listing and turned down Facebook's offer to boost it for a fee.
  3. It asked me once for my lowest price and when buyers could pick up, then checked the Marketplace inbox every few hours. Five people got in touch. For each one it drafted a reply and waited for my OK. One offered $30, and it proposed countering at $40 rather than dropping straight to my floor.
  4. The next morning two buyers wanted it: one that afternoon, one on Saturday. It laid out both, suggested the sooner one with Saturday as a backup, and let me choose. It sent my address only after I gave it the address to send.
  5. Once I confirmed the buyer had collected it and paid, it marked the listing sold and sent the other four a short note.

It sold for the asking price the day after the prompt. My part was approving each reply, choosing the buyer and giving the address; the agent never messaged anyone on its own. And no, it didn't give buyers a recipe for cake.

The whole sale on video (2 minutes, with sound and captions):

A goal that never finishes: Flipper

Selling one thing is a one-off goal, which moves to Done once nothing is left open. The Flipper goal is the standing kind: grow a NZ$200 budget by buying underpriced things on Facebook Marketplace and Trade Me and reselling them for a profit. Watches on Marketplace's free, furniture and appliance listings and on Trade Me start a run when something new is listed. Each run sorts the new titles by name and price alone, opens at most five, looks at every photo, and skips anything that needs a repair, like a freezer whose lid doesn't seal. A deal worth proposing comes with comparable sales, a resale estimate, the fuel for the round trip, the expected profit, a suggested offer and a pick-up time that fits my week. A ledger in its memory keeps the capital, the stock and each flip.

Every message to a seller, offer and purchase waits for my approval. Its first buy was a dryer for NZ$80 on Trade Me that should resell for NZ$150-180, and I pressed Buy Now myself: Claude in Chrome asks a person to confirm a purchase, and a background run has no one to ask.

Example: from issue to merged PR

Quarterdeck's own repo is looked after by two goals made from the ready-made *Work on new GitHub issues* and *Fix failing CI*. Neither has a schedule: each has a watch, a gh command checked every 5 minutes, and a run starts only when it sees something new. Here is the first issue they handled, start to finish:

  1. Claude went through the to-do list and roadmap with me, and we posted issue #1: the pane said "no schedule" for a goal that runs on a watch.
  2. Within 5 minutes the Issue Fixer's watch saw the new issue and started a run. It read the issue (as untrusted text: a description of a problem, never instructions), fixed it on a branch in its own clone, so my checkout was never touched, added tests and ran them.
  3. It proposed opening the pull request. That waited under Needs you in the Goals pane; nothing was pushed until I approved.
  4. Approved, the next run pushed the branch and opened PR #2. CI passed on all five checks, and I merged it, which closed the issue.

The run took 2 minutes. The PR says it was opened by a Quarterdeck goal, and the CI goal now watches main for that merge, ready to propose a fix if anything breaks.

An issue anyone can open is an obvious place to hide instructions for an agent, so the Issue Fixer only takes work from the repo's owner, members and collaborators, and it reads only their comments. When anyone else opens an issue, the run sees just the number and the author, and asks you under Needs you whether to work on it before reading a word. Pushing and opening a pull request wait for your approval in Quarterdeck's guard, not only in the instructions: the goal's tool rules name git push and gh pr create, and turn off other writes to GitHub (comments, gh api, gh auth). These rules match command names, so a script that pushes for it gets past them; running goals in a sandbox is on the roadmap.

A new issue often lacks the context to build it well, so a new Issue Fixer asks whether to wait for a refined label, and waits by default. The *Refine new issues* goal (the Issue Refiner) reads each new issue and the code it touches, asks you about every decision it can't settle from the code, and then proposes a spec: what is asked, the files involved, an approach and acceptance criteria. Once you approve, it posts the spec as a comment and adds refined, which starts the fixer. When only the reporter can answer something, it posts their questions instead and adds needs-clarification, and their reply starts it again. Only someone with triage rights can label an issue, so nobody else can label their own issue to get it built. To switch an Issue Fixer you made earlier, ask Claude to replace its "new issues" and "new issues from others" watches with one on issues labelled refined, and to update its instructions from the template.

In front of the refiner, the *Triage new issues* goal (Issue Triage) reads every new issue, whoever opened it, and proposes labels for the whole batch in one item: its kind and priority from your repo's own labels, a likely duplicate, and triaged. Its only write is labels you approved; it never comments, closes or edits an issue. Once a batch is labelled it asks you one question, "Which of these should be refined?", and answering with the numbers adds needs-refinement to just those (adding the label on GitHub does the same). A new Issue Refiner waits for that label by default, so an agent spends a run only on issues you picked:

new issue → Issue Triage → triaged → (you pick) → needs-refinement → Issue Refiner → refined → Issue Fixer → pull request

To have a refiner you made earlier wait for your pick, ask Claude to replace its "issues to refine" and "issues to refine from others" watches with one on issues labelled needs-refinement, and to update its instructions from the template.

Here's another one on video, from a to-do in the pane to the feature working live (80 seconds, with sound and captions). This time the Issue Fixer stopped to ask which of two designs to build before writing any code (issue #17, PR #18):

只显示了开头部分;其余内容请在仓库中阅读