World Monitor
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.
Check an MCP server before you install it — outside-in trust ratings for 7,000+ operators.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 7/12 | 30 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 | 7/100 |
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)
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
用 Stillos Ratings MCP 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 Stillos Ratings MCP,或回答中出现 Stillos Ratings MCP 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 Stillos Ratings MCP
Stillos Ratings MCP 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
A · 使用能连接 Stillos Ratings MCP 的应用
B · 其他 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 Stillos Ratings MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Stillos Ratings MCP 的应用
Cursor 暂时无法连接 Stillos Ratings MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Stillos Ratings MCP 的应用
VS Code 暂时无法连接 Stillos Ratings MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Stillos Ratings MCP 的应用
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
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。
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19日
注册名称已通过 GitHub 账户 stillmarcus24 验证,该账户拥有此仓库
代码最后更新于39天前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/stillmarcus24-stillos-ratings-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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。
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。
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)。
GitHub 仓库最后更新于39天前,最新版本(1.0.0)于上个月进入注册中心。
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。
同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu
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
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.
Manage monitors, status pages, incidents and maintenances in your openstatus workspace.
Validate oh-my-posh configurations and segment snippets against the official schema.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.
| 本项 Stillos Ratings MCP | World Monitor | openstatus | Oh My Posh Validator | Strata | Jitsu | |
|---|---|---|---|---|---|---|
| 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 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 1/4 | 4/4 |
| 许可证 | MIT | AGPL-3.0 | AGPL-3.0 | MIT | Apache-2.0 | MIT |
| 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 |
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。
Check an MCP server before you install it.
Installing an MCP server means handing a stranger's code a tool surface inside your client. There is no standard way to ask "should I?" — this is one. It answers from a public census of 7,000+ MCP operators, refreshed every 6 hours, rated from the outside, unasked, the way a credit bureau rates a borrower rather than the way a badge rates whoever applied for it.
Free. No key, no signup, no account. Every figure is independently recomputable.
npx stillos-ratings-mcp check api.mcp.ai
npx stillos-ratings-mcp findings npx stillos-ratings-mcp compare api.mcp.ai some-other-host.com
{
"mcpServers": { "stillos-ratings": { "command": "npx", "args": ["-y", "stillos-ratings-mcp", "mcp"] } } }
| Tool | What it answers |
|---|---|
check_mcp_server | Grade, rank, five scored dimensions, rail position, publisher/fleet concentration, and any dated finding for one host |
list_tool_surface_findings | Every operator currently carrying a dated tool-surface finding |
compare_mcp_servers | Up to 10 candidates side by side |
The headline signal is a tool surface that changed while the version string did not.
Two anonymous tools/list enumerations of the same endpoint, at different times. The serverInfo.version string was byte-identical in both. The tool set was not. Any client that pinned that version and approved its tool list was never asked to re-approve what it now exposes — and if one of the added tools takes an action (writes, sends, moves money, deletes), that matters.
This is an observation about change. It is not an accusation of malice, and this tool will never phrase it as one.
The public registry is far more concentrated than it looks. Measured 2026-10-04 across 39,321 registry entries from 23,281 publishers: the top 10 publishers control 19.0% of it, one GitHub account alone publishes 2,365 servers, and 34.8% of tool-bearing servers share a boilerplate tool set with a template fleet — while 20,980 publishers have exactly one server.
So every answer carries a fleet block: who publishes it, how many servers that publisher has, and how many others share its core tool set. A server that is 1 of 1,022 running the same template is a different proposition from a one-off, and that was the most decision-relevant fact nobody was reporting.
It is a structural observation about how a server was produced — not an accusation of bad faith, and a large publisher can still ship good software. Where the registry does not cover a host, the block says concentration was not measured, which is deliberately not the same sentence as "not a fleet".
NOT_RATED with an explicit warning. We enumerate 41.8% of the distinct remote-declaring hosts in the public registry (measured, as of 2026-10-04) — so absence is a statement about our reach, not about that operator. Unobserved is not attested safe.Recompute it. The board is sealed and public, the method is published in full, and the dimensions are arithmetic over a public census — so there is no judgement call to argue with and no appeal to make to us.
https://stillosdigitalholdings.com/ratings/n/ https://stillosdigitalholdings.com/notary/verify?hash= — every check_mcp_server answer carries the receipt_hash and a ready-made link in its recompute block (live example). Scope is integrity and timestamp only — it proves the board you are reading is the board that was sealed, not that any rating is "correct".GET https://stillosdigitalholdings.com/ratings/node?host= — free and unmetered. This package is a thin client over that endpoint, holds no credential, and can therefore leak none. Every answer it gives can be reproduced with curl.
MIT · Still OS Digital Holdings LLC, Wyoming