Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).
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。
SECURITY_SCORECARD_API_TOKEN, COMPANY_DOMAIN标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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": {
"securityscorecard": {
"command": "npx",
"args": [
"-y",
"@callmarcus/securityscorecard-mcp"
],
"env": {
"SECURITY_SCORECARD_API_TOKEN": "your-value",
"COMPANY_DOMAIN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add securityscorecard --env SECURITY_SCORECARD_API_TOKEN=your-value --env COMPANY_DOMAIN=your-value -- npx -y @callmarcus/securityscorecard-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"securityscorecard": {
"command": "npx",
"args": [
"-y",
"@callmarcus/securityscorecard-mcp"
],
"env": {
"SECURITY_SCORECARD_API_TOKEN": "your-value",
"COMPANY_DOMAIN": "your-value"
}
}
}
}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": {
"securityscorecard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@callmarcus/securityscorecard-mcp"
],
"env": {
"SECURITY_SCORECARD_API_TOKEN": "your-value",
"COMPANY_DOMAIN": "your-value"
}
}
}
}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。
COMPANY_DOMAIN env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7日
注册名称已通过 GitHub 账户 CallMarcus 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。
你需要填写:SECURITY_SCORECARD_API_TOKEN
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(2.0.0)于33天前进入注册中心。
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:Spec Driven Development, Remote Desktop Commander, SuperCollider
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Make sound with SuperCollider: synths, drums, chords, melodies and soundscapes over OSC.
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。
A community-built, comprehensive Model Context Protocol (MCP) server that integrates with the SecurityScorecard API. It runs over stdio, so it works with any MCP-compatible client — Claude Desktop, Claude Code, Cursor, VS Code, and others. It serves MCP protocol revision 2026-07-28 and stays compatible with 2025-era clients.
Published on npm as
@callmarcus/securityscorecard-mcpand listed in the MCP Registry asio.github.CallMarcus/securityscorecard-mcp.
Disclaimer: This is an independent, community-built open-source project. It is not affiliated with, endorsed by, sponsored by, or associated with SecurityScorecard, Inc. in any way. It is built solely against SecurityScorecard's publicly available API documentation. "SecurityScorecard" and all related names, marks, and logos are trademarks of SecurityScorecard, Inc. and are used here for identification purposes only. You must supply your own API credentials and comply with SecurityScorecard's terms of service.
No clone or build required. The server runs over stdio via npx, so any MCP-compatible client can launch it. npx -y always fetches the latest published version.
Most clients — Claude Desktop, Cursor, Cline, Windsurf, and others — share the same mcpServers JSON. Add this block to the client's MCP config:
{
"mcpServers": { "security-scorecard": { "command": "npx", "args": ["-y", "@callmarcus/securityscorecard-mcp"], "env": { "SECURITY_SCORECARD_API_TOKEN": "your-api-token-here", "COMPANY_DOMAIN": "example.com" } } } }
Where that config file lives:
| Client | Config file |
|---|---|
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Cursor | ~/.cursor/mcp.json (global) or .cursor/mcp.json (project) |
Replace the credentials with your own, then restart the client.
Claude Code — add it from the CLI instead:
claude mcp add security-scorecard \
--env SECURITY_SCORECARD_API_TOKEN=your-api-token-here \ --env COMPANY_DOMAIN=example.com \ -- npx -y @callmarcus/securityscorecard-mcp
On Windows, wrap the launcher in cmd /c: ... -- cmd /c npx -y @callmarcus/securityscorecard-mcp.
VS Code (Copilot) — uses a servers key with an explicit type, in .vscode/mcp.json:
{
"servers": { "security-scorecard": { "type": "stdio", "command": "npx", "args": ["-y", "@callmarcus/securityscorecard-mcp"], "env": { "SECURITY_SCORECARD_API_TOKEN": "your-api-token-here", "COMPANY_DOMAIN": "example.com" } } } }
# Clone the repository
git clone https://github.com/CallMarcus/security-scorecard-mcp.git cd security-scorecard-mcp
npm install
npm run build:fast
Then point your MCP client at the local build. For clients that use the mcpServers format (Claude Desktop, Cursor, …):
{
"mcpServers": { "security-scorecard": { "command": "node", "args": ["/path/to/security-scorecard-mcp/build/index.js"], "env": { "SECURITY_SCORECARD_API_TOKEN": "your-api-token-here", "COMPANY_DOMAIN": "example.com" } } } }
Important: Replace the path and credentials with your actual values, then restart your MCP client. (For Claude Code, run claude mcp add security-scorecard --env SECURITY_SCORECARD_API_TOKEN=your-api-token-here -- node /path/to/security-scorecard-mcp/build/index.js.)
The server (index.js) provides 9 specialized tools:
| Tool | Purpose |
|---|---|
security_dashboard | Score, grade, and key security metrics |
analyze_security_risks | Issue prioritization and risk analysis |
create_improvement_plan | Actionable remediation roadmaps |
discover_assets | Asset inventory with security context |
analyze_email_security | SPF/DMARC/DKIM analysis |
api_discovery | Search 535 API endpoints with hybrid semantic/keyword search |
analyze_issue_types | Granular issue type breakdowns |
validate_data_completeness | Cross-tool data verification |
query_security_data | Direct API access with discovery |
Each tool supports three response modes for token efficiency:
| Variable | Required | Description |
|---|---|---|
SECURITY_SCORECARD_API_TOKEN | Yes | Your API token |
COMPANY_DOMAIN | No | Default domain for queries |
DEBUG_MODE | No | Set true for verbose logging |
Optional rate limiting and caching:
REQUEST_CACHE_TTL_MS=300000
REQUESTS_PER_INTERVAL=5 REQUEST_INTERVAL_MS=1000
The server includes hybrid search (semantic + keyword) for finding SecurityScorecard API endpoints:
Use api_discovery to search for "email security"
This searches 535 indexed endpoints and returns matching paths with confidence scores, required parameters, and curl examples.
To update the API reference after changes:
npm run api:embed # Regenerate semantic embeddings
npm run api:update # Regenerate docs + embeddings
npm run build:fast # Recommended - uses esbuild (~130ms)
npm run build # TypeScript compiler (may OOM on some systems) npm test # Run tests
src/
index.ts # MCP server (9 tools) api/client.ts # SecurityScorecard API client integration/ # API discovery system docs/api/ # Self-contained API reference index.jsonl # Endpoint index (535 endpoints) index-embeddings.json # Semantic search embeddings build/ # Compiled JavaScript
npm test # Run test suite
Use the fast build instead:
npm run build:fast
Reinstall dependencies:
rm -rf node_modules
npm install npm run build:fast
Install for the platform that runs the server. Claude Desktop on Windows launches the server with Windows node, so if npm install ran under WSL the native modules (onnxruntime-node, sharp) only have linux binaries — the embeddings layer fails to load and api_discovery silently degrades to keyword-only search (results still come back, but confidence scoring is cruder). Run npm install && npm run build:fast from PowerShell or cmd in the repo directory instead — or keep two clones, one per platform.
build/index.js is correctnpx -y @callmarcus/securityscorecard-mcp (it should launch and wait silently on stdio)Your API token is invalid or expired. Get a new one from SecurityScorecard dashboard.
MIT