nightingale

Open-Source Alerting Expert English | 中文 🎯 What is Nightingale Nightingale is an open-source monitoring project that focuses on alerting. Similar to Grafana, Nightingale also connects with various existing data sources. However, while Grafana emphasizes visualization, Nightingale places greater...

CVE-2026-77254 MCP Atlassian: Unauthenticated HTTP MCP requests can use globally configured Jira and Confluence credentials

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

EUVD-2026-84743

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

CVE-2026-33032

CVE-2026-33032 / MCPwn 针对 nginx-ui MCP 认证绕过漏洞（公开名称为 MCPwn ）的非破坏性检测工具。通过两次 HTTP 请求即可在未认证的情况下完全接管任何运行受影响版本的 nginx-ui 实例。 目录 1. 快速概览 2. 漏洞概述 3. 技术深入分析 4. 检测策略 5. 安装 6. 使用方法 7. 输出示例 8. 与 CVE-2026-27944 联动 9. 修复建议 10. 负责任使用 11. 参考资料 12. 许可证 快速概览 漏洞概述 nginx-ui 暴露了一个模型上下文协议（MCP）接口，允许经过认证的操作员通过 JSON-RPC...

cve-2026-33032-scanner

CVE-2026-33032 扫描器 用于 Nginx-UI MCP 端点认证绕过的非破坏性漏洞扫描器 漏洞概述 CVE-2026-33032 是 nginx-ui 的模型上下文协议（MCP）集成中的一个认证绕过漏洞。/mcpmessage 端点在提供所有 MCP 工具访问权限的同时缺少认证中间件，允许远程攻击者： 读取 nginx 配置和状态 创建/修改/删除 nginx 配置文件 重启或重新加载 nginx 服务 窃取敏感配置数据 注入恶意配置以进行流量拦截 根本原因 1. 认证不对称 ：/mcp 端点需要认证，但 /mcpmessage 不需要： root@kitploit:...

siyuan-mcp-admin-takeover-cve-2026-66012-missing-authorization

CVE-2026-66012 — SiYuan MCP Unauthenticated Administrator Takeover Proof of Concept for CVE-2026-66012 CVSS 10.0 Critical, a missing-authorization vulnerability in SiYuan's MCP Model Context Protocol endpoint that allows an unauthenticated attacker to achieve administrator takeover and remote cod...

CVE-2026-61568

@zereight/mcp-gitlab is a Model Context Protocol server for GitLab. Versions prior to 2.1.30 expose the Streamable HTTP MCP endpoint without an effective Host or Origin allowlist. A malicious web page can use DNS rebinding to route browser requests to a victim's local MCP listener while preservin...

EUVD-2026-79999

@zereight/mcp-gitlab is a Model Context Protocol server for GitLab. Versions prior to 2.1.30 expose the Streamable HTTP MCP endpoint without an effective Host or Origin allowlist. A malicious web page can use DNS rebinding to route browser requests to a victim's local MCP listener while preservin...

Security Bulletin: Langflow is vulnerable to authentication bypass and insufficient session expiration

Summary Langflow provides API key-based authentication for programmatic access to flow execution and MCP endpoints. The MCP HTTP API credential resolvers do not apply the same AUTOLOGIN API-key guard that all standard authenticated endpoints enforce; when Langflow is in its default AUTOLOGIN...

CVE-2026-59822

A flaw was found in LiteLLM, a proxy server designed for Large Language Model LLM APIs. An unauthenticated attacker could exploit a vulnerability in the MCP Streamable HTTP endpoint. By using a fabricated Authorization header, the attacker could bypass the standard key validation, gaining...

CVE-2026-45018

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the...

CVE-2026-45019

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For sse and streamable-http...

CVE-2026-45019

Chainlit (a Python framework for building conversational AI applications) is affected by an SSRF vulnerability in its MCP integration. From version 2.4.0rc0 to 2.12.0 , deployments with features.mcp.enabled = true expose the POST /mcp endpoint without authentication. For SSE and streamable-http t...

EUVD-2026-42717

@arikusi/deepseek-mcp-server: Missing Authentication on Self-Hosted HTTP MCP Endpoint...

PT-2026-81492

Name of the Vulnerable Software and Affected Versions Chainlit versions 2.4.0rc0 through 2.11.x Description Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the 'POST /mcp' endpoint without authentication. The ConnectSseMCPRequest and...

CVE-2026-45018: Improper Neutralization of Special Elements used in an OS Command

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the...

PT-2026-81486

Name of the Vulnerable Software and Affected Versions Chainlit versions 2.4.0rc0 through 2.11.9 Description Deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the 'POST /mcp' endpoint without authentication. For stdio transport, the endpoint accepts a user-controlle...

PT-2026-66665

An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service DoS. The /mcp endpoint handler reads incoming payloads directly into system memory using a...

CVE-2026-66012

SiYuan before v3.7.2 contains a missing authorization vulnerability in the POST /mcp kernel endpoint, which is gated only by a general auth check model.CheckAuth with no admin-role or read-only enforcement. This exposes 31 MCP tools, including a file tool with list/read/write/delete/rename/copy...

EUVD-2026-49043

SiYuan before v3.7.2 contains a missing authorization vulnerability in the POST /mcp kernel endpoint, which is gated only by a general auth check model.CheckAuth with no admin-role or read-only enforcement. This exposes 31 MCP tools, including a file tool with list/read/write/delete/rename/copy...