firecrawl-mcp-server

Firecrawl MCP Server A Model Context Protocol MCP server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context. Big thanks to @vrknetha, @knacklabs for the initial implementation! Features Search the web and get full page...

damn-vulnerable-MCP-server

Cursor SSE Compatibility for Damn Vulnerable MCP This document provides an overview of the updates made to the Damn Vulnerable Model Context Protocol DVMCP project to make it compatible with Cursor's Server-Sent Events SSE implementation. Overview The original DVMCP project has been enhanced to...

EUVD-2026-67147

mcp-go accepted requests on its HTTP transports without checking the Host header. StreamableHTTPServer.ServeHTTP in server/streamablehttp.go and SSEServer.ServeHTTP in server/sse.go served any request arriving over a loopback connection regardless of the host it named, and the SSE transport's...

CVE-2026-34227

Nicht authentifizierte MCP-Schnittstelle + CORS-Bypass Slivers MCP-Server startet eine nicht authentifizierte SSE-Schnittstelle und sendet bei jeder Antwort Access-Control-Allow-Origin: zurück. Die mcp-go-Bibliothek validiert Content-Type nicht, sodass Simple Requests text/plain die...

MCP-Inspector-CVE-2025-49596

MCP Inspector CVE-2025-49596 Schwachstellenprüfer Dieses Skript prüft, ob ein MCP Inspector-Server anfällig für CVE-2025-49596 ist, ein Sicherheitsproblem, bei dem der /sse-Endpunkt auf nicht authentifizierte Anfragen reagiert fehlendes Authentifizierungstoken. Funktionsweise Das Skript sendet ei...

pentest-mcp

Pentest MCP Professioneller MCP-Server für Penetrationstests mit moderner Transport-/Authentifizierungsunterstützung und erweiterten Recon-Werkzeugen. Was gibt es Neues in 0.9.0 MCP-SDK auf @modelcontextprotocol/sdk@^1.26.0 aktualisiert MCP Inspector auf dem neuesten Stand gehalten...

studio

ShipSec Studio Open-Source-Plattform zur Orchestrierung von Sicherheits-Workflows. ShipSec befindet sich derzeit in aktiver Entwicklung. Wir optimieren die Plattform für einen stabilen Produktionseinsatz und leistungsstarke Sicherheitsabläufe. ShipSec Studio bietet eine visuelle DSL und...

sandbox-agent

Coding-Agenten in Sandboxen ausführen. Per HTTP steuern. Ein Server, der in Ihrer Sandbox läuft. Ihre App verbindet sich remote, um Claude Code, Codex, OpenCode, Cursor, Amp oder Pi zu steuern – mit Streaming von Ereignissen, Verwaltung von Berechtigungen und Sitzungen. Dokumentation — API-Refere...

Linux Distros Unpatched Vulnerability : CVE-2026-79780

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - rclone before v1.75.0 fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys during S3 redirect callbacks, allowing credentials to be preserved acros...

CVE-2026-53965

The MCP PHP SDK Composer package mcp/sdk is the official Model Context Protocol SDK for PHP. In versions 0.5.0 through 0.7.0, the HTTP client transport reads a Server-Sent Events response stream incrementally and appends each chunk to an in-memory buffer with no upper bound. The buffer is only...

CVE-2026-53965 MCP PHP SDK: Unbounded SSE buffer in HttpTransport enables client-side denial of service

The MCP PHP SDK Composer package mcp/sdk is the official Model Context Protocol SDK for PHP. In versions 0.5.0 through 0.7.0, the HTTP client transport reads a Server-Sent Events response stream incrementally and appends each chunk to an in-memory buffer with no upper bound. The buffer is only...

CVE-2026-53965

CVE-2026-53965 affects the MCP PHP SDK (Composer package mcp/sdk), versions 0.5.0 through 0.7.0 . The HttpTransport class's processSSEStream() method appends each 4 KiB read chunk to an in-memory buffer ($this->sseBuffer) with no upper bound ; the buffer is only flushed upon encountering the S...

CVE-2026-45019 Chainlit: SSRF via MCP SSE and streamable-http transports allows unauthenticated internal network access

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-2026-79780

rclone before v1.75.0 fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys during S3 redirect callbacks, allowing credentials to be preserved across scheme or host changes. Attackers observing network traffic from a trusted endpoint can capture reusable IBM IAM tokens on same-host...

CVE-2026-79780

rclone before v1.75.0 contains a credential exposure vulnerability in its S3 redirect callback handling. The tool fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys when following redirects, allowing credentials to persist across scheme or host changes . An attacker positioned to o...

CVE-2026-79780 rclone before v1.75.0 Credential Exposure via S3 Redirect

rclone before v1.75.0 fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys during S3 redirect callbacks, allowing credentials to be preserved across scheme or host changes. Attackers observing network traffic from a trusted endpoint can capture reusable IBM IAM tokens on same-host...

CVE-2026-79780 rclone before v1.75.0 Credential Exposure via S3 Redirect

rclone before v1.75.0 fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys during S3 redirect callbacks, allowing credentials to be preserved across scheme or host changes. Attackers observing network traffic from a trusted endpoint can capture reusable IBM IAM tokens on same-host...

EUVD-2026-65538

rclone before v1.75.0 fails to sanitize IBM IAM bearer tokens and SSE-C encryption keys during S3 redirect callbacks, allowing credentials to be preserved across scheme or host changes. Attackers observing network traffic from a trusted endpoint can capture reusable IBM IAM tokens on same-host...

CVE-2026-79666 Ech0 before 4.4.3 Missing Authorization via dashboard log endpoints

Ech0 before 4.4.3 fails to enforce administrator authorization on dashboard log endpoints, allowing any authenticated user to access system logs. Attackers with valid user sessions can query GET /api/system/logs and subscribe to SSE and WebSocket log streams to retrieve sensitive operational data...

CVE-2026-79666 Ech0 before 4.4.3 Missing Authorization via dashboard log endpoints

Ech0 before 4.4.3 fails to enforce administrator authorization on dashboard log endpoints, allowing any authenticated user to access system logs. Attackers with valid user sessions can query GET /api/system/logs and subscribe to SSE and WebSocket log streams to retrieve sensitive operational data...