Securityscorecard Mcp

io.github.CallMarcus由 GitHub 帳號 CallMarcus 發布v2.0.0更新於 Oct 26, 2026

Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).

已驗證STDIO僅桌面安全與監控商業與電商

概覽

AI 產生的概覽

非官方 MCP 伺服器,讓助理查詢 SecurityScorecard 的企業安全評分、風險、資產與郵件安全資訊。

可以做什麼
  • 讀取安全態勢:評分、等級、關鍵指標與問題類型細分
  • 分析風險並產生改善計畫
  • 盤點資產並檢查 SPF/DMARC/DKIM 郵件安全
  • 搜尋 SecurityScorecard API 參考並直接發出 API 查詢
  • 跨工具驗證資料完整性,支援精簡、標準、詳細三種回應模式
適用情境
適合需要讓助理取得某企業網域的第三方安全評分與風險背景、檢查郵件驗證設定,或在聊天用戶端內整理修補優先順序的情境。
執行需求
透過 npx 以 stdio 在本機執行,需要 Node.js 20 以上。需要 SecurityScorecard API 權杖,放在 SECURITY_SCORECARD_API_TOKEN 中;COMPANY_DOMAIN 為選用的預設網域。需要能連線至 SecurityScorecard API 的網路。
安裝前請注意
API 權杖屬於機密,會寫入用戶端設定檔,請妥善保護該檔案。本專案為獨立社群專案,與 SecurityScorecard 公司無關,使用時須遵守其服務條款。查詢會將企業網域傳送給 SecurityScorecard API;工具本身為唯讀查詢。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Securityscorecard Mcp,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

SSC MCP Server

[npm version] [License: MIT]

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-mcp and listed in the MCP Registry as io.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.

Quick Start

Prerequisites

  1. Node.js 20+ - Download
  2. SecurityScorecard API Token - Get from your SecurityScorecard dashboard

Option A — Install from npm (recommended)

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:

json
{  "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:

ClientConfig 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:

bash
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:

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"      }    }  }}

Option B — Run from source (for development)

bash
# Clone the repositorygit clone https://github.com/CallMarcus/security-scorecard-mcp.gitcd security-scorecard-mcp
# Install dependenciesnpm install
# Build (use build:fast to avoid memory issues)npm run build:fast

Then point your MCP client at the local build. For clients that use the mcpServers format (Claude Desktop, Cursor, …):

json
{  "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.)

Available Tools

The server (index.js) provides 9 specialized tools:

ToolPurpose
security_dashboardScore, grade, and key security metrics
analyze_security_risksIssue prioritization and risk analysis
create_improvement_planActionable remediation roadmaps
discover_assetsAsset inventory with security context
analyze_email_securitySPF/DMARC/DKIM analysis
api_discoverySearch 535 API endpoints with hybrid semantic/keyword search
analyze_issue_typesGranular issue type breakdowns
validate_data_completenessCross-tool data verification
query_security_dataDirect API access with discovery

Response Modes

Each tool supports three response modes for token efficiency:

  • minimal - Quick answers (15-50 tokens)
  • standard - Overview with context (200-300 tokens)
  • detailed - Comprehensive analysis (800+ tokens)

Environment Variables

VariableRequiredDescription
SECURITY_SCORECARD_API_TOKENYesYour API token
COMPANY_DOMAINNoDefault domain for queries
DEBUG_MODENoSet true for verbose logging

Optional rate limiting and caching:

REQUEST_CACHE_TTL_MS=300000REQUESTS_PER_INTERVAL=5REQUEST_INTERVAL_MS=1000

API Discovery

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:

bash
npm run api:embed    # Regenerate semantic embeddingsnpm run api:update   # Regenerate docs + embeddings

Development

Build Commands

bash
npm run build:fast   # Recommended - uses esbuild (~130ms)npm run build        # TypeScript compiler (may OOM on some systems)npm test             # Run tests

Project Structure

src/  index.ts               # MCP server (9 tools)  api/client.ts          # SecurityScorecard API client  integration/           # API discovery systemdocs/api/                # Self-contained API reference  index.jsonl            # Endpoint index (535 endpoints)  index-embeddings.json  # Semantic search embeddingsbuild/                   # Compiled JavaScript

Testing

bash
npm test             # Run test suite

Troubleshooting

Build fails with out of memory

Use the fast build instead:

bash
npm run build:fast

"Cannot find module" errors

Reinstall dependencies:

bash
rm -rf node_modulesnpm installnpm run build:fast

Semantic search degrades to keyword-only (Windows + WSL)

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.

Your client doesn't see the server

  1. Double-check the config file location for your client (see Quick Start)
  2. For a from-source install, verify the path to build/index.js is correct
  3. Restart the client completely
  4. Sanity-check that the server starts on its own: npx -y @callmarcus/securityscorecard-mcp (it should launch and wait silently on stdio)

API returns 401 Unauthorized

Your API token is invalid or expired. Get a new one from SecurityScorecard dashboard.

License

MIT

Links

來源:README.md,提交 af4fad8

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

2
  1. v2.0.0最新Oct 4, 2026
  2. v1.2.0Sep 16, 2026

評分

已滿足適用檢查項的 40%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。