CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

cve-cache

weiseer/cve-cache-mcp
STDIOregistry active
Summary

A cached CVE and GitHub Security Advisory feed that lets your agent check vulnerabilities without hitting NVD or GHSA APIs directly. Exposes four tools: lookup_cve for individual records, find_for_package to scan npm/PyPI/Cargo/Maven/Go dependencies, list_recent_critical for high-severity issues from the past week, and severity_summary for counts by bucket. The pitch is speed and cost: sub-100ms lookups instead of multi-second API calls, and you avoid the token overhead of parsing verbose NVD JSON. Normalized across ecosystems so you get consistent schema whether you're auditing a Python or Rust project. Install globally via npm, wire it into Claude Desktop or any MCP client with npx, and you're querying the cache locally.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

@weiseer/cve-cache-mcp

Recent CVE + GHSA cache as a stdio MCP server.

Probe P-005 by weiseer.

What it does

Cached, structured snapshot of recent CVE + GitHub Security Advisory records — for AI agents auditing dependencies or screening new packages.

Your agent can:

  • lookup_cve — full record for one CVE/GHSA ID
  • find_for_package — all CVEs affecting a package by ecosystem (npm/PyPI/Cargo/Maven/Go)
  • list_recent_critical — recent high-severity CVEs (default: 7-day, CVSS ≥ 7)
  • severity_summary — counts by severity bucket

Why use this instead of your agent querying NVD itself

Agent DIYcve-cache
Source queryNVD JSON feeds + GHSA GraphQL1 MCP call
Token cost (NVD records are large)$0.05-0.20$0 free / $0.00005 paid
Latency2-10 seconds<100ms
Cross-ecosystem normalizationPer-source schemaPre-normalized

Install

npm install -g @weiseer/cve-cache-mcp

Use with Claude Desktop / Cursor / Cline / Continue / Windsurf

{
  "mcpServers": {
    "cve-cache": {
      "command": "npx",
      "args": ["-y", "@weiseer/cve-cache-mcp"]
    }
  }
}

License

Apache-2.0. Catalog data: derived from public CVE/NVD/GHSA feeds (CC0/public domain).

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Configuration

CVE_CACHE_URL

Override remote snapshot URL

CVE_CACHE_LOCAL_ONLY

Skip remote fetch

Categories
Security & Pentesting
Registryactive
Package@weiseer/cve-cache-mcp
TransportSTDIO
UpdatedMay 30, 2026
View on GitHub

Related Security & Pentesting MCP Servers

View all →
Exploit Intelligence Platform — CVE, Vulnerability and Exploit Database

com.exploit-intel/eip-mcp

Real-time CVE, exploit, and vulnerability intelligence for AI assistants (350K+ CVEs, 115K+ PoCs)
Semgrep

semgrep/mcp

A MCP server for using Semgrep to scan code for security vulnerabilities.
666
Pentest

dmontgomery40/pentest-mcp

NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap, go/dirbuster, nikto, JtR, hashcat, wordlist building, and more.
137
Notebooklm Mcp Secure

pantheon-security/notebooklm-mcp-secure

Security-hardened NotebookLM MCP with post-quantum encryption
68
Pentest Mcp Server

cyanheads/pentest-mcp-server

Offline methodology engine for authorized penetration testing, CTF, and security research.
1
AI Firewall MCP

io.github.akhilucky/ai-firewall-mcp

Multi-agent LLM security layer detecting prompt injection and jailbreaks.