Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/badchars/cve-mcp/claude-mdgit clone --depth 1 https://github.com/badchars/cve-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/badchars/cve-mcp/claude-md)<a href="https://agentmods.dev/instructions/badchars/cve-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/badchars/cve-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00845 | $0.00845 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
cve-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CVE MCP
Project Context
Bu proje hackbrowser-mcp, cloud-audit-mcp ve github-security-mcp'den sonra dorduncu MCP projesi. AI agent'a CVE/vulnerability intelligence veriyor — NVD, EPSS, KEV, Exploit-DB, MITRE ATT&CK uzerinden.
Neden MCP?
CVE arastirmasi her pentester/security researcher'in gunluk isi. Simdi: NVD'ye git, CVE ara, EPSS score'a bak, exploit var mi kontrol et, KEV listesinde mi bak. Hepsi ayri site, ayri API. MCP ile agent hepsini tek seferde yapar.
Hedef Kullanim
User: "CVE-2024-3400 hakkinda ne biliyorsun? Exploit var mi?"
Agent: → NVD'den CVE detaylarini ceker (CVSS, CWE, affected products)
→ EPSS score kontrol eder (exploitation probability)
→ KEV listesinde mi bakar (CISA known exploited)
→ Exploit-DB'de PoC arar
→ "CVSS 10.0, EPSS 97%, KEV listesinde, 3 public exploit var.
Palo Alto PAN-OS command injection. Patch ASAP."
Veri Kaynaklari
- NVD API v2: CVE detaylari, CVSS scores, CPE matching (API key opsiyonel, rate limit arttirir)
- EPSS: Exploit Prediction Scoring System (first.org, public API, key gereksiz)
- KEV: CISA Known Exploited Vulnerabilities catalog (JSON feed, key gereksiz)
- Exploit-DB: Public exploit database (API veya scrape)
- MITRE ATT&CK: Technique mapping (STIX/TAXII veya static JSON)
- GitHub Advisory Database: GitHub'in kendi CVE veritabani (GraphQL, GITHUB_TOKEN ile)
- OSV: Open Source Vulnerabilities (Google, public API)
npm Publish Hedefi
Bu proje npm'de yayinlanacak: npx cve-mcp
- Dependency'ler hafif olmali (sadece MCP SDK + zod + fetch)
- API key gereksiz (NVD, EPSS, KEV hepsi public)
- Opsiyonel: NVD_API_KEY rate limit arttirir
Technical Stack
- Runtime: Bun + TypeScript (Node.js uyumlu, npm publish icin)
- Protocol: MCP (stdio transport)
- SDK: @modelcontextprotocol/sdk
- HTTP: Native fetch (no axios)
- Architecture: hackbrowser-mcp/cloud-audit-mcp/github-security-mcp pattern'i — ToolDef/ToolContext/ToolResult, Zod schemas, allTools array
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 72 lines · 845 tokens per session scan A f4b502bba858
cve-mcp CLAUDE.md is an instructions file published in the GitHub repository badchars/cve-mcp (24 stars, last pushed 2d ago), licensed MIT. It adds 845 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
stride-gpt AGENTS.md
AGENTS.md instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
AiSOC AGENTS.md
AGENTS.md instructions for beenuar/AiSOC, covering learned user preferences and learned workspace facts.
prismor AGENTS.md
AGENTS.md instructions for PrismorSec/prismor, covering agents.md, primary objectives, start here, how to work in this repo and 1. treat security guidance as product logic.
From-LLMs-to-Secure-Agents AGENTS.md
AGENTS.md instructions for RenatoMignone/From-LLMs-to-Secure-Agents, covering agent instructions, run contract, policy map and invariants.
Mingyi-Atlas CLAUDE.md
Claude Code instructions for MingyiSecLab/Mingyi-Atlas, covering claude.md, project overview, common commands, architecture and modes and prompts.
numasec AGENTS.md
AGENTS.md instructions for FrancescoStabile/numasec, covering numasec agent guide, operating rules, branches, product direction and product messaging direction.