# cve-mcp-server-security-intelligence

cve-mcp-server-security-intelligence — a skill that runs a local MCP server and hands the agent 27 tools for CVE work: CVSS and EPSS scores, CISA KEV status, exploit hunting and a composite risk score.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 229 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/cve-mcp-server-security-intelligence/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/cve-mcp-server-security-intelligence

## What it does

The skill installs an MCP server that runs on your machine over stdio and gives the agent 27 tools backed by 21 APIs, among them NVD, EPSS, CISA KEV, MITRE ATT&CK, Shodan, VirusTotal, GreyNoise and GitHub. Ask about a CVE and you get the CVSS score, the affected products, the EPSS exploitation probability and whether it sits in the KEV list. It also hunts public proof-of-concept code on GitHub and Exploit-DB, checks IP reputation, and pulls up to 20 CVEs in one batch.

Risk collapses into a single number out of 100: CVSS times 10, EPSS times 30, 20 extra for KEV membership, 10 more when a PoC exists, capped at 100. That score sorts a CVE list and feeds a report with priorities and mapped ATT&CK techniques.

Python 3.10 or newer is the baseline. Keys for the paid services are optional, and the tools return less without them, though the server still starts. Get an NVD key early because rate limits bite otherwise. Outbound HTTPS is the only traffic it makes.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill cve-mcp-server-security-intelligence -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/cve-mcp-server-security-intelligence/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/cve-mcp-server-security-intelligence/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill cve-mcp-server-security-intelligence -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/cve-mcp-server-security-intelligence/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill cve-mcp-server-security-intelligence -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/cve-mcp-server-security-intelligence/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/cve-mcp-server-security-intelligence
```

2. **Manually: put the files in place**
- File: `.github/skills/cve-mcp-server-security-intelligence/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill cve-mcp-server-security-intelligence -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/cve-mcp-server-security-intelligence
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/cve-mcp-server-security-intelligence/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill cve-mcp-server-security-intelligence -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/cve-mcp-server-security-intelligence/SKILL.md

## When to use it
- score a CVE for real-world exploitation risk
- rank a batch of CVEs before a patch window
- find public proof-of-concept code for a vulnerability
- check an IP against threat intelligence feeds
- turn a vulnerability list into a prioritised report

## Example prompts
- Check whether `CVE-2021-44228` is in CISA KEV and find public exploits for it.
- Rank these CVEs by risk and draft a short report on each one.
- What is the EPSS score for `CVE-2024-3400`, and is there a PoC?

## Similar
- [CVE Analyzer](https://affpapa.org/en/nevibecode/agents/cve-analyzer.md) — subagent · ★ 1627 repo stars
- [EchelonGraph CVE & Exposure](https://affpapa.org/en/nevibecode/mcp/echelongraph-cve-exposure.md) — MCP server · ★ 25 repo stars
- [cve-poc-generator](https://affpapa.org/en/nevibecode/skills/cve-poc-generator.md) — skill · 236 installs
- [security-review](https://affpapa.org/en/nevibecode/skills/factory-ai-security-review.md) — skill · 168 installs
- [security-engineer](https://affpapa.org/en/nevibecode/agents/josstei-security-engineer.md) — subagent · ★ 489 repo stars
- [review-security](https://affpapa.org/en/nevibecode/agents/review-security.md) — subagent · ★ 587 repo stars

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
