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。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

CommandVault

作者:geronco版本 1.0.0i★ –i在云端运行
注册名称io.github.geronco/commandvault

安装

概览

作者提供的说明(英文原文)

Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在云端运行
  • 传输方式: Streamable HTTP
  • 分类: 搜索与 AI 记忆

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://commandvault.ai/api/mcp

在终端中运行这条命令

claude mcp add --transport http commandvault https://commandvault.ai/api/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "commandvault": {
      "url": "https://commandvault.ai/api/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "commandvault": {
      "type": "http",
      "url": "https://commandvault.ai/api/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://commandvault.ai/api/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。

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6日

  • ✓ 通过

    作者与仓库一致

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

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

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 7223 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7223 个服务器的 77% 更新
  • 基础检查结果等于或优于此分类中其他 7223 个服务器的 100%

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

CommandVault 安全吗?

它在 1 项适用的基础检查中通过了 1 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?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.0.0)于10天前进入注册中心。

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。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ 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

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT3天前更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT44天前更新
安装

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。

CommandVault library

AI commands from commandvault.ai: prompts, CLAUDE.md / AGENTS.md templates, Cursor rules, Claude Code slash commands and subagents, Agent Skills and MCP servers. Every item has fill-in {{blanks}} and links back to its page, where you can fill the blanks in the browser. Entries marked tested on the site were run in Claude Code and Codex before publishing.

This repo is synced automatically every day from the site. To suggest a change, comment on the item's page on commandvault.ai (pull requests to the generated files are overwritten by the next sync).

Use it from your AI tool

MCP server (no key needed):

claude mcp add --transport http commandvault https://commandvault.ai/api/mcp

Setup for Cursor, VS Code, Codex, Claude Desktop and Gemini CLI: commandvault.ai/mcp.

Claude Code plugin (MCP server + a lookup skill + /vault command):

/plugin marketplace add geronco/commandvault-library

/plugin install commandvault@commandvault

Layout

FolderWhat's in it
commands/ /Prompts, templates and checklists as Markdown with front matter
skills/ /SKILL.mdAgent Skills, ready to copy into .claude/skills/
mcp-servers/ .jsonMCP server configs (mcpServers format)
data/commands.json, data/commands.csvEverything in one file, for datasets and scripts

License

Content: CC BY 4.0. Credit "CommandVault (commandvault.ai)" with a link. Code (scripts, workflow, plugin): MIT.

Third-party skills (skills/third-party/) and MCP servers are linked, not copied: each file names the author, source repo and license, and the original keeps its own license.

_Synced from commandvault.ai on 2026-11-06: 240 items._

Agent Skills (75)

Description
Accessibility audit (Addy Osmani) · webAudit and fix web accessibility issues against WCAG 2.2.
AI search optimization (Marketing Skills) · webHelps your content get cited by ChatGPT, Perplexity, Claude and Google AI Overviews.
Brainstorming before building (Superpowers) · webTurns a rough idea into an agreed design through focused questions before any code is written.
Canvas design (Anthropic) · webCreate original posters and static art as PNG or PDF, guided by a design philosophy.
Claude API reference (Anthropic) · webUp-to-date guidance for building apps on the Claude API and Anthropic SDKs.
Claude Code automation recommender (Anthropic) · webAnalyzes your codebase and recommends hooks, subagents, skills and MCP servers to set up.
Claude Code hook development (Anthropic) · webHow to write Claude Code hooks that validate, block or automate tool use.
CLAUDE.md improver (Anthropic) · webAudits your repo's CLAUDE.md files, scores them and makes targeted improvements.
Cloudflare Agents SDK (Cloudflare) · webBuild stateful AI agents on Cloudflare with the agents package.
Cloudflare platform guide (Cloudflare) · webHelps pick and use the right Cloudflare products for apps, APIs, agents and storage.
CodeQL scan (Trail of Bits) · webBuilds a CodeQL database and runs data-flow and taint analysis to find vulnerabilities.
Conversation to spec (Matt Pocock) · webTurns what you've discussed into a structured spec and files it in your issue tracker.
Conversion rate optimization (Marketing Skills) · webReviews a page or form and suggests changes and experiments to lift conversions.
dbt analytics engineering (dbt Labs) · webBuild and modify dbt models the right way: ref/source, tests and checking results with dbt show.
Deploy to Vercel (Vercel) · webDeploys the current project to Vercel and returns a preview or production URL.
Doc co-authoring workflow (Anthropic) · webA structured workflow for writing specs, proposals and decision docs together with Claude.
Excel spreadsheets (Anthropic) · webCreate, clean and analyze Excel and CSV files with working formulas and formatting.
Exploratory data analysis (K-Dense) · webCareful, local exploratory analysis of data files with leakage, missingness and outlier checks.
Expo native UI (Expo) · webBuild native-feeling Expo screens with Apple HIG styling, native controls and SF Symbols.
Find bugs in your branch (Sentry) · webReviews the changes on your branch for bugs, security holes and quality issues.
Frontend design (Anthropic) · webPush UI work past generic defaults toward a distinctive, deliberate visual design.
Gemini API development (Google) · webGoogle's guide to writing correct, current code against the Gemini API in Python and TypeScript.
Git worktrees for isolation (Superpowers) · webSets up an isolated git worktree with a clean, passing baseline before feature work starts.
GitHub Actions security review (Sentry) · webFinds exploitable flaws in GitHub Actions workflows, like pwn requests and script injection.
Gradio apps (Hugging Face) · webBuild Gradio web UIs and demos in Python, from simple forms to chatbots.
Grill me (Matt Pocock) · webHas Claude interview you relentlessly to stress-test a plan or design.
Hugging Face Hub CLI (Hugging Face) · webUse the hf CLI to download, upload and manage models, datasets, Spaces and jobs on the Hub.
Improve codebase architecture (Matt Pocock) · webScans a codebase for places to deepen modules and presents them as a visual HTML report.
Iterate on a PR until green (Sentry) · webLoops on a pull request, fixing CI failures and review feedback until checks pass.
LLM fine-tuning on HF Jobs (Hugging Face) · webFine-tune language and vision models with TRL or Unsloth on Hugging Face cloud GPUs.
Marketing copywriting (Marketing Skills) · webWrites and rewrites landing, pricing and product page copy that sounds human and converts.
MCP server builder (Anthropic) · webBuild well-designed MCP servers in Python or TypeScript that wrap an external API.
Neon Postgres (Neon) · webNeon's guide to connections, branching, migrations, autoscaling and search on Neon Postgres.
PDF toolkit (Anthropic) · webRead, create, merge, split, fill and OCR PDF files from inside Claude.
Playwright CLI browser automation (Microsoft) · webControl a real browser from the terminal with playwright-cli: navigate, click, fill, test.
Postgres best practices (Supabase) · webSupabase's prioritized Postgres rules for schema, indexes, RLS, migrations and slow queries.
PowerPoint decks (Anthropic) · webBuild, edit and QA PowerPoint presentations, from pitch decks to template updates.
Property-based testing (Trail of Bits) · webWrite and review property-based tests with Hypothesis, fast-check, proptest and more.
React & Next.js performance (Vercel) · webVercel's ranked rules for faster React and Next.js code: waterfalls, bundles, rendering.
React composition patterns (Vercel) · webPatterns for flexible React components: compound components, context and fewer boolean props.

| [React

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx