US Safety Recalls

搜索与获取

by martc03

汇集 NHTSA 车辆召回及 FDA 食品与药品召回数据,提供 4 个工具支持安全风险排查。

什么是 US Safety Recalls

汇集 NHTSA 车辆召回及 FDA 食品与药品召回数据,提供 4 个工具支持安全风险排查。

README

Cybersecurity Vulnerability Intelligence MCP Server

Unified vulnerability intelligence from 4 government data sources in a single MCP server. Get enriched CVE lookups with CVSS scores, active exploitation status, exploitation probability, and ATT&CK techniques in one call.

SourceWhat It ProvidesUpdate Frequency
NIST NVD 2.0CVE details, CVSS scores, descriptions, references, CWE classificationsContinuous
CISA KEVActively exploited vulnerabilities catalog, remediation deadlinesDaily
FIRST.org EPSSExploitation probability scores (0-1) predicting likelihood of exploitation in next 30 daysDaily
MITRE ATT&CKAdversary techniques mapped to CVEsQuarterly

Tools

vuln_lookup_cve — Enriched CVE Lookup

The killer feature. Look up any CVE and get intelligence from all 4 sources in a single call.

  • Input: { cveId: "CVE-2021-44228" }
  • Returns: NVD details + CVSS score + KEV exploitation status + EPSS probability + ATT&CK techniques

vuln_search — Search CVEs

Search the NVD by keyword, severity, and date range. Optionally filter to only actively exploited (KEV) vulnerabilities.

  • Input: { keyword: "apache log4j", severity: "CRITICAL", hasKev: true, limit: 20 }

vuln_kev_latest — Recently Exploited Vulnerabilities

Get vulnerabilities recently added to CISA's Known Exploited Vulnerabilities catalog.

  • Input: { days: 7, limit: 20 }

vuln_kev_due_soon — Upcoming Remediation Deadlines

Get KEV entries with remediation deadlines approaching. Critical for federal compliance.

  • Input: { days: 14, limit: 20 }

vuln_epss_top — Highest Exploitation Probability

Get CVEs most likely to be exploited in the next 30 days based on EPSS machine learning model.

  • Input: { threshold: 0.7, limit: 20 }

vuln_trending — Newly Published Critical CVEs

Get recently published high/critical severity CVEs from the NVD.

  • Input: { days: 3, severity: "CRITICAL", limit: 20 }

vuln_by_vendor — Vendor Vulnerability Assessment

Search CVEs for a specific vendor/product. Cross-references with CISA KEV to flag actively exploited issues.

  • Input: { vendor: "microsoft", product: "windows", limit: 20 }

Use Cases

  • Vulnerability triage: Look up a CVE and instantly know if it's actively exploited, its EPSS score, and what ATT&CK techniques apply
  • Patch prioritization: Combine KEV status + EPSS scores to prioritize remediation
  • Compliance tracking: Monitor upcoming CISA KEV remediation deadlines
  • Threat intelligence: Track trending CVEs and newly weaponized vulnerabilities
  • Vendor risk assessment: Assess a vendor's vulnerability exposure and active exploitation status

Quick Start

Glama (hosted)

Install from Glama.ai.

Apify (hosted)

json
{
  "mcpServers": {
    "cybersecurity": {
      "url": "https://cybersecurity-vuln-mcp.apify.actor/mcp"
    }
  }
}

Claude Desktop / Claude Code

json
{
  "mcpServers": {
    "cybersecurity": {
      "command": "node",
      "args": ["path/to/servers/cybersecurity-vuln-mcp/dist/stdio.js"],
      "env": {
        "NVD_API_KEY": "your-key-here"
      }
    }
  }
}

Local (stdio)

bash
git clone https://github.com/martc03/gov-mcp-servers.git
cd gov-mcp-servers/servers/cybersecurity-vuln-mcp
npm install && npm run build
node dist/stdio.js

Environment Variables

VariableRequiredDescription
NVD_API_KEYNoNVD API key for higher rate limits (50 req/30s vs 5 req/30s). Register here.

Caching

Data SourceTTLNotes
NVD CVE lookups1 hourPer-CVE
CISA KEV catalog2 hoursFull catalog
EPSS scores24 hoursPer-CVE
ATT&CK mappingsStaticBundled with server

Architecture

  • Protocol: MCP over stdio (Glama/local) or Streamable HTTP (Apify)
  • Runtime: Node.js 18+, TypeScript
  • Data: Direct API calls to free government data sources, zero cost
  • Caching: In-memory with configurable TTLs

Other Servers in This Repo

This repository contains 13 MCP servers for US government data. See each server's README for details.

ServerToolsData Sources
us-safety-recalls-mcp4NHTSA recalls, FDA recalls
natural-disaster-intel-mcp4FEMA disasters, NOAA weather, USGS earthquakes
federal-financial-intel-mcp4SEC EDGAR, CFPB complaints, BLS employment
immigration-travel-mcp3Visa bulletins, border wait times
environmental-compliance-mcp3EPA air quality, HUD foreclosures
gov-contracts-mcp4SAM.gov contracts, USAspending
court-records-mcp4PACER, federal court records
public-health-mcp4NIH clinical trials, FDA adverse events
business-entity-mcp4SEC company search, SBA resources
regulatory-monitor-mcp4Federal Register, regulations.gov
grant-finder-mcp4Grants.gov, USAspending
competitive-intel-mcp4SEC filings, patent data, trade data

A REST API gateway with 45 endpoints is also available at govdata-api.netlify.app.

Attribution

  • NVD: This product uses data from the NVD API but is not endorsed or certified by the NVD.
  • EPSS: Data provided by FIRST.org (https://www.first.org/epss/).
  • ATT&CK: Registered trademark of The MITRE Corporation. Licensed under Apache 2.0.
  • KEV: CISA Known Exploited Vulnerabilities Catalog, US Government public domain.

Custom MCP Server Development

Need a custom MCP server for your business? Visit mcpdev.netlify.app or email codee.mcpdev@gmail.com.

License

MIT

常见问题

US Safety Recalls 是什么?

汇集 NHTSA 车辆召回及 FDA 食品与药品召回数据,提供 4 个工具支持安全风险排查。

相关 Skills

谷歌视频工具

by bwbernardweston18

热门

>

搜索与获取
未扫描4.5k
热门

股票投研9点分析框架,覆盖基本面/财务/竞品/估值/宏观/情绪等维度

搜索与获取
未扫描4.5k

SEO审计工具

by amdf01-debug

热门

搜索与获取
未扫描4.5k

相关 MCP Server

by Anthropic

热门

Puppeteer 是让 Claude 自动操作浏览器进行网页抓取和测试的 MCP 服务器。

这个服务器解决了手动编写 Puppeteer 脚本的繁琐问题,适合需要自动化网页交互的开发者,比如抓取动态内容或做端到端测试。不过,作为参考实现,它可能缺少生产级的安全防护,建议在可控环境中使用。

搜索与获取
89.1k

Brave 搜索

编辑精选

by Anthropic

热门

Brave Search 是让 Claude 直接调用 Brave 搜索 API 获取实时网络信息的 MCP 服务器。

如果你想让 AI 助手帮你搜索最新资讯或技术文档,这个工具能绕过传统搜索的限制,直接返回结构化数据。特别适合需要实时信息的开发者,比如查 API 更新或竞品动态。不过它依赖 Brave 的 API 配额,高频使用可能受限。

搜索与获取
89.1k

网页抓取

编辑精选

by Anthropic

热门

Fetch 是 MCP 官方参考服务器,让 AI 能抓取网页并转为 Markdown 格式。

这个服务器解决了 AI 直接处理网页内容时格式混乱的问题,适合需要让 Claude 分析在线文档或新闻的开发者。不过作为参考实现,它缺乏生产级的安全配置,你得自己处理反爬虫和隐私风险。

搜索与获取
89.1k

评论