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

Spurvik

✓ Brand-named GitHub · github.com/spurvik

作者:spurvik版本 1.0.9i★ 0i电脑或云端官方网站 ↗
注册名称io.github.spurvik/spurvik-mcp-server

安装方法

What it does

EU AI Act Art. 50 URL & C2PA checks, Art. 12/14 snippets, HMAC receipts, DPO questionnaire answers.

  • Connects 电脑或云端
  • Account or key Cloud: Works without a key · add Authorization if you have one (often raises limits) · Local: No key needed
  • Category 其他

为什么排在这里

此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列

1. 在 Claude 连接器目录中否
2. 团队实测过否
3. 适合泰国用户否
4. 不计星标的使用量34/100热度 14 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0
5. 登记日期2026-11-18

用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。

质量: 基础检查通过 4/5 项(仅展示,不用于排序)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 Spurvik。按照 https://mcp.popnx.com/i/spurvik-mcp-server.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 4/5 项检查 · 你的提问会经过开发者的服务器(console.spurvik.com) · ✓ 命令已检查 2026年11月19日

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 · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Spurvik
    Remote MCP server URL · 地址https://console.spurvik.com/api/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsSpurvik

  4. 试一试

    用 Spurvik 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 Spurvik,或回答中出现 Spurvik 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

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Spurvik
    Connection · 地址https://console.spurvik.com/api/mcp
  3. 在聊天中选择 Spurvik

    开启新聊天,输入前先从插件列表中选择 Spurvik

  4. 试一试

    用 Spurvik 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Spurvik,或回答中出现 Spurvik 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 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user spurvik https://console.spurvik.com/api/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 Spurvik 在列表中并显示已连接

  4. 试一试

    用 Spurvik 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Spurvik,或回答中出现 Spurvik 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

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Spurvik 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Spurvik,或回答中出现 Spurvik 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 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Spurvik 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Spurvik,或回答中出现 Spurvik 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 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

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 →

通过网页连接的应用使用的地址

地址https://console.spurvik.com/api/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Spurvik 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user spurvik https://console.spurvik.com/api/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "spurvik": {
      "url": "https://console.spurvik.com/api/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "spurvik": {
      "type": "http",
      "url": "https://console.spurvik.com/api/mcp"
    }
  }
}

安装在电脑上

Claude Code

claude mcp add --scope user spurvik -- npx -y spurvik-mcp-server --root .

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "spurvik": {
      "command": "npx",
      "args": [
        "-y",
        "spurvik-mcp-server",
        "--root",
        "."
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "spurvik": {
      "command": "npx",
      "args": [
        "-y",
        "spurvik-mcp-server",
        "--root",
        "."
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "spurvik": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "spurvik-mcp-server",
        "--root",
        "."
      ]
    }
  }
}

需要你填写的值

  • SPURVIK_MCP_ROOT env
    可选的工作区根路径,用于在未传入 --root 时对未封装调用进行静态扫描
    查看英文原文Optional workspace root path for static unwrapped-call scans when --root is not passed.
  • SPURVIK_API_KEY 机密 env
    可选的 Spurvik API 密钥(spurvik_live_...),用于与 console.spurvik.com 关联项目的遥测数据
    查看英文原文Optional Spurvik API key (spurvik_live_...) for project-linked telemetry with console.spurvik.com.
  • SPURVIK_HMAC_SECRET 机密 env
    可选的服务器端 HMAC-SHA256 签名密钥(至少 16 个字符),用于本地收据检查。
    查看英文原文Optional server-side HMAC-SHA256 signing secret (>= 16 chars) for local receipt inspection.
  • Authorization 机密 HTTP header
    可选的 Bearer spurvik_live_... 令牌,用于与项目关联的控制台调用(对于 10 个无需密钥的只读工具不需要)。
    查看英文原文Optional Bearer spurvik_live_... token for project-linked console calls (not required for the 10 zero-key read-only tools).

说明为自动翻译,变量名保持原样;不确定时请查看原文。

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。

一览

每周下载量i
447/周
连接方式
电脑或云端
传输方式
stdio, streamable-http
最新版本i
1.0.9
分类i
其他
发布到注册中心i
2026年11月18日
代码最后更新i
2026年11月18日
最近检查
2026年11月19日
作者
spurvik
软件包
npm: spurvik-mcp-server
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。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月19日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • spurvik_setup_snippet

    Return a setup snippet for openai, anthropic, google-genai, vercel-ai-sdk, mastra, openai-agents, or langgraph. Provider clients are wrapped with withSpurvik. The Vercel AI SDK snippet passes spurvikMiddleware to wrapLanguageModel. The Mastra snippet calls withSpurvikMastra. The

  • spurvik_find_unwrapped_calls 看起来像是对 AI 下的指令

    Heuristic static scan of one directory inside the workspace root for AI client calls that are not passed through withSpurvik, spurvikMiddleware, withSpurvikMastra, withSpurvikModel, withSpurvikModelProvider, withSpurvikLangGraph, or spurvikInterrupt. A StateGraph constructor is r

  • spurvik_explain_receipt

    Explain the fields of an HMAC provenance receipt JSON. If signingSecret is passed, or SPURVIK_SIGNING_SECRET is set, check the HMAC locally with `verifyProvenanceSignature`, which checks that the record's signed fields still match the HMAC-SHA-256 signature. It does not show that

  • spurvik_marking_hooks

    Explain how to plug your own Article 50(2) marking into marking.text or marking.media. Spurvik does not mark content. withSpurvik and spurvikMiddleware log the call and attach an HMAC receipt. A hook runs only when you supply one. The signed text trailer is an application-level b

  • spurvik_scan_live_url

    Scan one public page (bare domain or http(s) URL, for example stepnetwork.dk) for AI chat widgets and AI SDKs and check whether a visible EU AI Act Article 50(1) notice is present. Returns the host, HTTP status, findings, the suggested notice language, a one-line badge.js fix, th

  • spurvik_batch_scan_domains

    Scan 1 to 10 public domains or http(s) URLs (for example an agency's client sites) for AI chat widgets and AI SDKs, and check each page for a visible EU AI Act Article 50(1) notice. Every entry is checked first: if any entry is localhost, a private or reserved IP or an internal h

  • spurvik_classify_ai_act_risk

    Self-assessment of an AI system under the EU AI Act from a few answers: prohibited (Article 5), high-risk (Annex III), Article 50 transparency only, minimal risk, or outside the EU. Returns the duties with their dates and the Spurvik setup steps. Not legal advice and not a decisi

  • spurvik_generate_art50_badge

    Generate a copy-paste EU AI Act Article 50 notice: a badge.js tag or a React snippet, in any of the 24 EU languages, with a preview of the notice text. The language is inferred from a domain-like systemName when locale is omitted.

  • spurvik_check_image_c2pa_url

    C2PA JUMBF manifest & CDN-strip checker for one public https image URL (PNG, JPEG or WebP, up to 4 MB), ahead of EU AI Act Art. 50(2) machine-readable marking. Returns the format, byte size and file name, whether a C2PA (Content Credentials) manifest is embedded, the signature an

  • spurvik_vendor_questionnaire_answers

    Zero-network, deterministic Markdown answers to the five EU AI Act questions enterprise buyers ask in vendor security questionnaires and DPO RFPs: Q1 Art. 50(1) notice and 2 Dec 2026 Art. 50(2) provenance, Q2 Art. 12 cryptographic event logging (keyed HMAC-SHA256 inputHash/output

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19日

  • ✓ 通过

    作者与仓库一致

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

  • ✓ 通过

    仍在维护

    代码最后更新于昨天

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 275 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✕ 未通过

    工具描述中没有隐藏指令

    有 1 个工具描述包含看起来像是对 AI 下指令的文字。安装前请先阅读下方的内容

已公开的漏洞(OSV.dev)

尚未检查

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/spurvik-mcp-server.svg)](https://mcp.popnx.com/en/servers/spurvik-mcp-server)

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“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20653 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 20653 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 20653 个服务器的 59%

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

Spurvik 安全吗?

它在 5 项适用的基础检查中通过了 4 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?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于昨天,最新版本(1.0.9)于昨天进入注册中心。

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。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

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

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万3天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92742个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582514个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
Spurvik
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
运行位置云端或安装在电脑上都可以在云端运行,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4/54/44/44/41/44/4
许可证MITAGPL-3.0AGPL-3.0MITApache-2.0MIT
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。

packages/mcp

Local stdio MCP server for Cursor, VS Code, and other MCP clients. Build this directory from source. It is "private": true at version 1.0.6. The published npm package is spurvik-mcp-server@1.0.6 (MIT), from https://github.com/spurvik/spurvik.

It depends on spurvik-sdk@^1.0.7 from the npm registry, on packages/core in this repository, and on @modelcontextprotocol/sdk 1.32.1. The eight tools are read-only. Six run locally and do not use the network. spurvik_scan_live_url sends one public URL to https://console.spurvik.com/api/v1/sandbox/scan (8-second timeout, User-Agent: spurvik-mcp-server/1.0.6), and spurvik_batch_scan_domains sends up to 10 the same way; localhost, private or reserved IPs and internal hosts are refused before any request, and nothing is logged.

The SDK logs an AI call and attaches an HMAC receipt. Marking hooks are the caller's. Spurvik does not mark content. spurvik_classify_ai_act_risk is a deterministic engineering mapping aid, not legal advice and not a decision under Article 6. riskTier in a snippet is a sample value. Set your own classification (as provider or deployer); Spurvik does not classify your use case.

The lockfile installs spurvik-sdk@^1.0.7 from the npm registry. Then rebuild the plugin bundle with node packages/mcp/scripts/bundle-plugin.mjs. From spurvik-mcp-server@1.0.4, the bundled SDK matches spurvik@1.0.8: an overridden decision is not approved. spurvik-mcp-server@1.0.2 on npm still treats an overridden decision as approved.

Build from the repo root:

pnpm --filter packages/mcp build

The client starts the built file and passes the project directory with --root or SPURVIK_MCP_ROOT. The server refuses to start or to scan without that directory. spurvik_find_unwrapped_calls reads only inside it.

node packages/mcp/dist/index.js --root .

A missing signing secret throws only when a receipt check needs one. The value is not logged. The scanner skips files named .env or .env.* (any case), including through symlinks and hard links. Windows-only name forms are not handled. Cyrillic and other look-alike letters are not treated as the ASCII names they resemble. The temp directory named by TMPDIR, TEMP, or TMP is refused as a workspace root. On /mnt/ /Users/ , Public is not another user's home; any other name is refused unless it is the process user or the profile named by USERPROFILE or LOCALAPPDATA.

Tools

spurvik_setup_snippet

Return a setup snippet for openai, anthropic, google-genai, vercel-ai-sdk, mastra, openai-agents, or langgraph. Provider clients are wrapped with withSpurvik. The Vercel AI SDK snippet passes spurvikMiddleware to wrapLanguageModel. The Mastra snippet calls withSpurvikMastra. The OpenAI Agents snippet calls withSpurvikModelProvider. The LangGraph snippet calls withSpurvikLangGraph and spurvikInterrupt. The snippet is built from the installed spurvik exports. riskTier is a sample value. Set your own classification (as provider or deployer); Spurvik does not classify your use case. The SDK logs the call and attaches an HMAC receipt. It does not mark content.

spurvik_find_unwrapped_calls

Heuristic static scan of one directory inside the workspace root for AI client calls that are not passed through withSpurvik, spurvikMiddleware, withSpurvikMastra, withSpurvikModel, withSpurvikModelProvider, withSpurvikLangGraph, or spurvikInterrupt. A StateGraph constructor is reported when the file does not call withSpurvikLangGraph. A bare interrupt() call is reported when the file does not call spurvikInterrupt or resolveLangGraphInterrupts. The scan reads .ts, .tsx, .js, .jsx, .mjs, .cjs, .mts, and .cts files. It does not read .md or .mdc files. Results are file:line. The line number is 1-based and counts every newline, including comments and strings. This is a heuristic, so it can miss a call or report one that is already wrapped. The scan does not change files and does not use the network. Paths that leave the workspace, including '..', are rejected. The scanner skips files named .env or .env.* (any case), including through symlinks and hard links.

spurvik_explain_receipt

Explain the fields of an HMAC provenance receipt JSON. If signingSecret is passed, or SPURVIK_SIGNING_SECRET is set, check the HMAC locally with verifyProvenanceSignature, which checks that the record's signed fields still match the HMAC-SHA-256 signature. It does not show that a notice was shown, that output is marked, or that your system meets the Act. The signing secret is not logged. Omit the secret to explain the fields without checking.

spurvik_marking_hooks

Explain how to plug your own Article 50(2) marking into marking.text or marking.media. Spurvik does not mark content. withSpurvik and spurvikMiddleware log the call and attach an HMAC receipt. A hook runs only when you supply one. The signed text trailer is an application-level binding you can opt into. It is not, by itself, an Article 50(2) machine-readable mark.

spurvik_scan_live_url (new in 1.0.5)

Input { url }: a public http(s) URL or a bare domain such as stepnetwork.dk (normalized to https://stepnetwork.dk/). Scans one page through the hosted console for AI chat widgets and AI SDKs and checks for a visible Article 50(1) notice. Returns JSON with host, status, score, detectedWidgets, detectedSdks, art50NoticeDetected, a one-line badgeSnippet, reportUrl (https://console.spurvik.com/report?domain= ), sandboxUrl (https://console.spurvik.com/sandbox?scan= ), portfolioUrl (https://console.spurvik.com/portfolio), upgradeUrls (proWhiteLabelAndAuditVault, doneForYou24hSetup; from 1.0.6 both carry &appUrl= so the signup form is prefilled), and from 1.0.6 statusShieldUrl and statusShieldMarkdown. statusShieldMarkdown is one line a coding agent can offer to add to the project README.md:

[![EU AI Act Art. 50](https://console.spurvik.com/api/v1/badge/status.svg?domain=stepnetwork.dk)](https://console.spurvik.com/report?domain=stepnetwork.dk)

The console builds the shield SVG from a live check of the host's frontpage. When the console cannot be reached, times out, or answers without a scan, it returns offlineFallback: true with the same links and snippet instead of an error. localhost, .local/.internal hosts, private, loopback, link-local and reserved IPv4/IPv6 literals and non-default ports are refused with isError: true before any request. The tool is open-world (openWorldHint: true).

spurvik_batch_scan_domains (new in 1.0.6)

Input { domains }: 1 to 10 public http(s) URLs or bare domains, for example an agency's client sites. Every entry goes through the same check as spurvik_scan_live_url first. If any entry is refused (localhost, private or reserved IP, internal host, credentials, non-default port, not http(s)), the whole batch returns isError: true with rejected positions and nothing is sent. Duplicate hosts are scanned once. Each host is one GET https://console.spurvik.com/api/v1/sandbox/scan call with an 8-second timeout, at most 4 at once. (The console's POST /api/v1/sandbox/batch-scan accepts only same-origin browser requests from /portfolio, so the stdio server does not use it.) Returns JSON with totalDomains, scannedDomains, gapsFound (page read, AI chat widget or AI SDK found, no Art. 50(1) notice), offlineFallbacks, duplicatesRemoved, and one row per host with host, status, detectedWidgets, detectedSdks, art50NoticeDetected, gap, reportUrl, sandboxUrl, badgeSnippet, statusShieldUrl and statusShieldMarkdown. It also returns portfolioUrl and upgradeUrls (teamAgencyPack: Team €79/mo, doneForYouPerSite: Done-For-You €199 once per site; excl. VAT). A host that times out, is rate-limited or cannot be reached gets offlineFallback: true in its row; the batch still returns. The console rate-limits scans per client address (about 15 per minute), so a second full batch within a minute can come back as fallback rows. The tool is open-world (openWorldHint: true).

spurvik_classify_ai_act_risk (new in 1.0.5)

Input { useCase, domain?, interactsWithHumans?, generatesSyntheticMedia?, makesAutomatedDecisionsAboutPeople? }. domain is general or an Annex III area (biometrics, critical_infrastructure, education, employment_hr, essential_services_credit, law_enforcement, migration_border, justice_democracy). Deterministic, zero-network mapping to prohibited_art5, high_risk_annex_iii, limited_transparency_art50 or minimal_risk, with the signals used, obligations and dates, recommended Spurvik controls, interactiveClassifierUrl (https://console.spurvik.com/risk-check) and upgradeUrls (Pro €19/mo, Team €79/mo with the Annex IV draft, Done-For-You €199 once; excl. VAT). Omitted flags are inferred from fixed keywords in useCase. The use-case text is not stored or echoed. scopeNote: "Engineering mapping aid; not legal advice."

spurvik_generate_art50_badge (new in 1.0.5)

Input { locale?, position?, theme?, systemName?, attribution? }. Zero-network Article 50(1) notice in any of the 24 official EU languages: a one-line , a Next.js , the WordPress plugin (https://spurvik.com/r/spurvik-eu-ai-act-wp.zip), the Framer component (https://spurvik.com/r/spurvik-framer-badge.tsx) and the shadcn/v0 registry item (https://spurvik.com/r/article-50-badge.json). attribution defaults to true (Free) and shows a subtle "Art. 50 · Spurvik" link; attribution: false writes data-attribution="false", which is white-label on Pro (€19/mo) or Done-For-You (€199 once). The language is inferred from a domain-like systemName when locale is omitted. systemName is stripped of HTML/JSX attribute characters.

spurvik_setup_snippet notes also link the shareable report (https://console.spurvik.com/report), Pro (https://console.spurvik.com/signup?plan=pro) and the €199 Done-For-You 24h setup (https://console.spurvik.com/signup?plan=concierge).

The handlers and their JSON Schemas are exported from @spurvik/mcp/tools (scanLiveUrl, batchScanDomains, classifyAiActRisk, generateArt50Badge, SCAN_LIVE_URL_INPUT_JSON_SCHEMA, BATCH_SCAN_DOMAINS_INPUT_JSON_SCHEMA, CLASSIFY_RISK_INPUT_JSON_SCHEMA, ART50_BADGE_INPUT_JSON_SCHEMA).

Claude Code plugin

plugins/spurvik/.mcp.json starts the server bundled inside the plugin. The command is node. The arguments are ${CLAUDE_PLUGIN_ROOT}/bin/spurvik-mcp.mjs, --root, and ${CLAUDE_PROJECT_DIR}. That file is bundled from packages/mcp 1.0.6 with node packages/mcp/scripts/bundle-plugin.mjs. The same eight read-only tools are spurvik_setup_snippet, spurvik_find_unwrapped_calls, spurvik_explain_receipt, spurvik_marking_hooks, spurvik_scan_live_url, spurvik_batch_scan_domains, spurvik_classify_ai_act_risk, and spurvik_generate_art50_badge. This plugin entry is not one of the Cursor or VS Code examples below: it runs bin/spurvik-mcp.mjs from the plugin directory, not packages/mcp/dist/index.js.

Cursor

.cursor/mcp.json at the workspace root:

{

"mcpServers": { "spurvik": { "command": "node", "args": ["${workspaceFolder}/packages/mcp/dist/index.js", "--root", "${workspaceFolder}"] } } }

Use an absolute path when the workspace root is not this repo:

{

"mcpServers": { "spurvik": { "command": "node", "args": ["/absolute/path/to/the/repo/packages/mcp/dist/index.js", "--root", "/absolute/path/to/the/repo"] } } }

VS Code

.vscode/mcp.json:

{

"servers": { "spurvik": { "type": "stdio", "command": "node", "args": ["${workspaceFolder}/packages/mcp/dist/index.js", "--root", "${workspaceFolder}"] } } }

What it does not do

  • It does not call the network, exce

只显示了开头部分;其余内容请在仓库中阅读