agentmods.dev

cve-mcp

cve-mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from mukul975/cve-mcp-server. Its token cost is not measured, scanned A, original, Apache-2.0.

An MCP server for working with CVE records, which are public identifiers for known software security vulnerabilities. It runs locally with Python and requires several environment settings.

In plain words
What is it for?
Use it as a configured CVE-related MCP connection after supplying the required API, logging, timeout, and retry settings.
Why use it?
The input does not describe its available operations, but it identifies the configuration needed to run the server and contact vulnerability data.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 1.5krepo +104 1mo ago A scan tokens not measured original Apache-2.0

Good fit Use it as a configured CVE-related MCP connection after supplying the required API, logging, timeout, and retry settings.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/mukul975/cve-mcp-server/cve-mcp
View source ↗ mukul975/cve-mcp-server mahipal.engineer
About the project

CVE MCP Server is a Model Context Protocol server that gives Claude tools for gathering and correlating cybersecurity information from vulnerability and threat-intelligence APIs. It is for security professionals, developers, and teams that need to investigate CVEs, exploitation risk, affected systems, and related evidence.

mukul975/cve-mcp-server · 1,481 stars · on GitHub · mahipal.engineer

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mukul975/cve-mcp-server

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote 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.

agentmods badge for cve-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/mukul975/cve-mcp-server/cve-mcp/github.svg)](https://agentmods.dev/mcp/mukul975/cve-mcp-server/cve-mcp)
Your own site
<a href="https://agentmods.dev/mcp/mukul975/cve-mcp-server/cve-mcp"><img src="https://agentmods.dev/badge/mcp/mukul975/cve-mcp-server/cve-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cve-mcp

Your own site · 80×15
<a href="https://agentmods.dev/mcp/mukul975/cve-mcp-server/cve-mcp"><img src="https://agentmods.dev/badge/mcp/mukul975/cve-mcp-server/cve-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

cve-mcp 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 9d 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.

.mcp.json · 16 lines

What it actually says

{
  "cve-mcp": {
    "command": "python",
    "args": [
      "-m",
      "cve_mcp.server"
    ],
    "cwd": "D:\\MCP\\cve-mcp-server",
    "env": {
      "NVD_API_KEY": "",
      "AUDIT_LOG_PATH": "",
      "REQUEST_TIMEOUT": "30",
      "MAX_RETRIES": "3"
    }
  }
}
Changes

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.

  1. 9d ago First seen · 16 lines scan A 38f938bb6b9c

Subscribe to this mod's changes

cve-mcp is an MCP server published in the GitHub repository mukul975/cve-mcp-server (1,481 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

CVESecuritycisa-kevclaude-aicybersecuritydevsecopsepss
Related

Other mcp servers, from other repositories

purify-feeds-mcp

MCP server "purify-feeds-mcp" as configured in eason4kim-rocket/purify-feeds-mcp. Runs in Docker (ghcr.io/eason4kim-rocket/purify-feeds-mcp:1.0.1). Needs 2 environment variables to run.

eason4kim-rocket/purify-feeds-mcp · not measured

patch-tuesday

MCP server for Microsoft Patch Tuesday security updates (MSRC Security Update Guide). Runs locally from the patch-tuesday-mcp Python package.

jonnybottles/patch-tuesday-mcp · not measured

vulnerability-mcp-server

MCP server "vulnerability-mcp-server" as configured in CedricG-dev/nvd-mcp. Runs locally from the vulnerability-mcp-server Python package.

CedricG-dev/nvd-mcp · not measured

cyber-intel-mcp

CVE search, vulnerability database, EPSS exploit prediction, KEV, IP reputation & threat feed. Remote server at cyber-intel-mcp-production.up.railway.app.

FoundryNet/cyber-intel-mcp · not measured

mcp-simple-tool

MCP server "mcp-simple-tool" as configured in firetix/vulnerability-intelligence-mcp-server. Runs locally from the mcp-simple-tool Python package.

firetix/vulnerability-intelligence-mcp-server · not measured

nist-nvd-mcp-server

Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE. Runs locally from the @cyanheads/nist-nvd-mcp-server npm package. Needs 3 environment variables to run.

cyanheads/nist-nvd-mcp-server · not measured