cve-mcp-server

🛡️ CVE MCP 服务器 AI 驱动的安全情报触手可及——28 个工具 + 一键triagecve 编排器，24 个数据源，一个协议。 一个生产级别的模型上下文协议（MCP）服务器 ，将 Claude 变成全能的安全分析师。无需在 NVD、EPSS、CISA KEV、Shodan、VirusTotal 和 GreyNoise 之间切换 15 个以上的浏览器标签页，只需向 Claude 提出一个问题，即可在数秒内获得关联情报。基于 Python、FastMCP、httpx、aiosqlite、Pydantic v2 和 defusedxml 构建。 问题所在： 对单个 CVE...

hexstrike-ai

HexStrike AI MCP Agents v6.0 AI 驱动的 MCP 网络安全自动化平台 先进的人工智能驱动渗透测试 MCP 框架，集成 150+ 安全工具和 12+ 自主 AI 代理 📋 新功能 • 🏗️ 架构 • 🚀 安装 • 🛠️ 特性 • 🤖 AI 代理 • 📡 API 参考 关注我们的社交账号 架构概览 HexStrike AI MCP v6.0 采用多代理架构，具备自主 AI 代理、智能决策和漏洞情报能力。mermaid %%init: "themeVariables": "primaryColor": "b71c1c", "secondaryColor":...

burp-ai-agent

Custom AI Agent 连接 Burp Suite 与现代 AI 的桥梁。 关于名称的说明： 此扩展以 Custom AI Agent （原名 Burp AI Agent ）的名称发布。更名是为了符合 PortSwigger 的 BApp Store 命名要求，并避免与 Burp Suite 内置的 Burp AI 提供方混淆。GitHub 仓库（github.com/six2dez/burp-ai-agent）、文档站点（burp-ai-agent.six2dez.com）以及配置目录（/.burp-ai-agent/）为保持连续性，仍沿用 burp-ai-agent 标识。...

diaphora-mcp

Читать на русском языке Diaphora MCP Diaphora MCP 是一个用于自动二进制差异分析的 MCP（模型上下文协议）服务器。它通过 MCP 协议连接 Diaphora（差异分析引擎）和 IDA Pro（反汇编器），使得 AI 代理（如 Claude Code）能够执行二进制文件比较、发现安全补丁并分析变更。 特性 导出 ：将分析后的 .i64 / .idb 数据库转换为 Diaphora SQLite 格式（通过 idat.exe 无头模式） 差异分析 ：比较两个导出的数据库，按匹配类型和比率过滤结果 漏洞分析...

Gideon

██████╗ ██╗██████╗ ███████╗ ██████╗ ███╗ ██╗ ██╔════╝ ██║██╔══██╗██╔════╝██╔═══██╗████╗ ██║ ██║ ███╗██║██║ ██║█████╗ ██║ ██║██╔██╗ ██║ ██║ ██║██║██║ ██║██╔══╝ ██║ ██║██║╚██╗██║ ╚██████╔╝██║██████╔╝███████╗╚██████╔╝██║ ╚████║ ╚═════╝ ╚═╝╚═════╝ ╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ 自主网络安全运营与红队攻击代理 由Requie 构建...

threat-modeling-mcp-server

Servidor MCP de Modelado de Amenazas Un servidor de Protocolo de Contexto de Modelo MCP para modelado de amenazas integral con validación automática de código. Tabla de Contenidos Resumen Comandos de Inicio Rápido Características Clave Requisitos Previos Instalación Ejecución con Kiro CLI Gestión...

refreshing-mcp-tool

Esto no está realmente terminado ni listo aún, pero quería dejar el código subido al repositorio. Esto básicamente implementa el protocolo de base de datos de F5, «mcp», que opera a través de un socket de dominio UNIX. Eso significa que necesitas un shell en el dispositivo F5 antes de poder usar...

beelzebub v3.9.1

Beelzebub Deception Runtime Framework Beelzebub is an open-source deception runtime that deploys adaptive, LLM-powered decoy services across SSH, HTTP, TCP, TELNET, and MCP protocols. It goes beyond passive honeypots by actively engaging attackers in realistic interactions, collecting high-fideli...

EUVD-2026-68103

argocd-mcp 0.8.0 binds its HTTP transport to every network interface and accepts MCP sessions without requiring caller credentials when ARGOCDAPITOKEN is configured. Attackers who can reach the listener can invoke the full tool surface using the operator's stored token to create applications,...

Authentication Bypass Using an Alternate Path or Channel

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Authentication Bypass Using an Alternate Path or Channel via the OAuth2 passthrough fallback in MCPRequestHandler.processmcprequest in...

CVE-2026-11719: Missing Authorization

An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers. While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol...

CVE-2026-32625

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol MCP server integration resolves $VAR placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any...

CVE-2026-5323

The CVE-2026-5323 entry affects priyankark a11y-mcp (up to 1.0.5), specifically the A11yServer function in src/index.js, causing a server-side request forgery. Exploitation requires a local position. An exploit has been made public. Upgrade to version 1.0.6 to resolve, with patch id e3e11c9e8482b...

Interpretation Conflict

Overview Affected versions of this package are vulnerable to Interpretation Conflict in the JSON-RPC and MCP protocol message parsing. An attacker can bypass intermediary inspection or cause cross-implementation inconsistencies by sending protocol messages with non-standard field casing or Unicod...

CVE-2026-27896

The Go MCP SDK used Go's standard encoding/json.Unmarshal for JSON-RPC and MCP protocol message parsing in versions prior to 1.3.1. Go's standard library performs case-insensitive matching of JSON keys to struct field tags — a field tagged json:"method" would also match "Method", "METHOD", etc...

CVE-2026-27896

The CVE-2026-27896 concerns the Go MCP SDK, affected in versions prior to 1.3.1, where Go’s json.Unmarshal (case-insensitive field matching) could accept non-standard JSON-RPC/MCP field casing. This violates JSON-RPC 2.0’s exact field names and could allow messages to bypass intermediary inspecti...

PT-2026-22069

Name of the Vulnerable Software and Affected Versions Go MCP SDK versions prior to 1.3.1 Description The Go MCP SDK used Go's standard encoding/json.Unmarshal for JSON-RPC and MCP protocol message parsing. Go's standard library performs case-insensitive matching of JSON keys to struct field tags,...

CVE-2025-61929 Cherry Studio allows one-click on a specific URL to cause a command to execute

Cherry Studio is a desktop client that supports for multiple LLM providers. Cherry Studio registers a custom protocol called cherrystudio://. When handling the MCP installation URL, it parses the base64-encoded configuration data and directly executes the command within it. In the files...

EUVD-2025-33778

Cherry Studio is a desktop client that supports for multiple LLM providers. Cherry Studio registers a custom protocol called cherrystudio://. When handling the MCP installation URL, it parses the base64-encoded configuration data and directly executes the command within it. In the files...