SUNGLASSES
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
作者提供的说明(英文原文)
Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
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。
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。
选择你使用的 AI 应用,然后复制设置。
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"yotta-verify": {
"command": "npx",
"args": [
"-y",
"@yottameta/yotta-verify-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add yotta-verify -- npx -y @yottameta/yotta-verify-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"yotta-verify": {
"command": "npx",
"args": [
"-y",
"@yottameta/yotta-verify-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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"yotta-verify": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@yottameta/yotta-verify-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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
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9日
注册名称已通过 GitHub 账户 YottaMeta 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
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
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 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。
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–,最新版本(0.4.3)于2个月前进入注册中心。
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 Node.js。
同一分类中有:SUNGLASSES, KillerSkills, Draugr
同一分类中其他作者的服务器,按星标数排序。
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
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
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。
Language : English · 中文
yotta-verify-mcp · 元信MCP (YuanXin MCP)
YottaMeta's pre-install security scanner for Agent skills , exposed as a stdio MCP server. Before you install any skill, plugin or MCP server, it runs a deterministic static scan — prompt injection, malicious patterns, SKILL.md integrity and permissions — and returns a verdict , an audited badge , a CI gate and a report as MCP tools. Activates when configuring the 元信 MCP server in an MCP client, wiring a trust-scan into an agent / workflow, or calling the MCP tools. Zero dependencies (Python 3.8+ standard library); Windows + Linux + macOS; fully local and offline — no network calls, no execution of the scanned code.
The skill / plugin market has a trust problem: a 2025 survey of 22,511 skills found 140,963 issues, and 36% contain prompt injection. 元信 MCP gives you a deterministic answer before you install — the same scan as the yotta-verify CLI, exposed as four MCP tools so any MCP client (Claude, VS Code, Codex, Cursor, …) can call it.
It is a pre-install verifier , not a sandbox and not a runtime monitor: it only reads files and prints a report. It never executes the scanned code, never connects to the network for the scan, and never fixes anything.
| Advantage | Description |
|---|---|
| Trust before install | A deterministic verdict for any skill / MCP server, instead of "trust me" |
| Zero dependency | Python 3.8+ standard library; no daemon / database / network |
| Fully local offline | Scans directories and npm tarballs on disk; nothing is executed or uploaded |
| Drop into any MCP client | Standard stdio MCP server — configure the server, and the four tools appear |
| Family synergy | Same rules table as yotta-verify (single source); verdicts merge with yotta-vetter / yotta-security-audit |
| Free & open | MIT; the whole scanner is free |
| Tool | What it does |
|---|---|
scan_skill | Pre-install scan: target (dir / .tgz / npm package) → verdict + severity counts + findings |
generate_badge | Audited badge: local SVG + shields.io URL; folds in validate / vetter / audit / version / tests |
gate_check | CI gate: fail when the worst severity exceeds max_severity (default medium) |
get_report | Verification report: Markdown or JSON, same format as the CLI |
MCP configuration is optional. An AI agent may show you the target config file, the exact mcpServers JSON, and the effect, then wait for your explicit consent before writing anything. If you decline, use the bundled CLI scanner directly; the scan result is unchanged.
scan_skillScan a skill directory or package before install.
| Param | Type | Required | Meaning |
|---|---|---|---|
target | string | yes | Skill directory path, .tgz / .tar.gz path, or npm package name (auto npm pack to a temp dir, then scan) |
Returns a JSON result: verdict, severity counts, and findings (prompt injection / malicious patterns / SKILL.md integrity).
generate_badgeGenerate an audited badge (local SVG + shields.io URL).
| Param | Type | Meaning |
|---|---|---|
target | string | Optional: scan this to derive the verdict |
verdict | string | Optional: set the verdict directly |
validate | string | Optional: pass / fail (validate-skill result) |
vetter / audit | string | Optional: external verdicts to fold in |
version | string | Optional: version label. Defaults to the scanner (yotta-verify) version (e.g. 0.1.1) |
tests | integer | Optional: engine test count |
out | string | Optional: write the SVG to this path |
Note: the badge's
versionsegment reflects the version of the bundled scanning engine
(yotta-verify), which may differ from the MCP package version. Pass
versionto override.
gate_checkCI pre-install gate.
| Param | Type | Meaning |
|---|---|---|
target | string | Required: dir / package to scan |
max_severity | string | Optional: info / low / medium / high / critical (default medium) |
Returns pass, verdict, worst, max_severity and an exit code.
get_reportGenerate a verification report.
| Param | Type | Meaning |
|---|---|---|
target | string | Required: dir / package to scan |
format | string | Optional: json / markdown (default markdown) |
out | string | Optional: write the report to this path |
This is a local, offline, static scan:
The package also ships a SKILL.md so an agent can explain how to configure and use the MCP server with explicit user consent. Pick any of the four methods below (skill files come from npm; GitHub can be slow without a proxy).
# Optional China mirror: npm config set registry https://registry.npmmirror.com
npx -y @yottameta/yotta-verify-mcp --agent # install to the agent's default user-level skills dir npx -y @yottameta/yotta-verify-mcp --dir # point to the skills dir itself (e.g. ~/.codex/skills)
--agent installs to that agent's default user-level directory; --list shows each agent's default directory.--dir installs to the given directory.npx -y @yottameta/yotta-verify-mcp.git clone https://github.com/YottaMeta/yotta-verify-mcp.git <your-skills-dir>/yotta-verify-mcp
On the GitHub repository YottaMeta/yotta-verify-mcp, click Code → Download ZIP, unzip it and put the yotta-verify-mcp folder into the agent's skills directory.
bash install.sh --agent <name> # install to the agent's default user-level directory
bash install.sh --dir # install to the given directory bash install.sh --list # list agents -> default directories
Repository validation includes the MCP engine suite and a documentation consent regression:
# MCP engine suite (Python 3.8 / 3.13)
python scripts/test_yotta_verify_mcp.py
node --test test/docs-consent.test.js
python scripts/yotta_verify_mcp.py
References: references/trust-checklist.md (pre-install trust checklist for MCP servers / plugins).
MIT © YottaMeta — see LICENSE.