EUVD-2026-36984

Unauthenticated Broken Access Control in Royal MCP = 1.4.2 versions...

CVE-2026-40775

Unauthenticated Broken Access Control in Royal MCP = 1.4.2 versions...

CVE-2026-40775 WordPress Royal MCP plugin <= 1.4.2 - Broken Access Control vulnerability

Unauthenticated Broken Access Control in Royal MCP = 1.4.2 versions...

PT-2026-49419

Unauthenticated Broken Access Control in Royal MCP = 1.4.2 versions...

PT-2026-49607

Name of the Vulnerable Software and Affected Versions LangBot versions 4.10.7 and earlier Description Authenticated users can execute arbitrary commands on the server with the privileges of the LangBot service due to an inadequate authorization boundary when adding or changing an STDIO MCP server...

GHSA-76G7-M3XW-X9GR MCP Toolbox for Databases has an Origin Validation Error

The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced...

Origin Validation Error

Overview Affected versions of this package are vulnerable to Origin Validation Error in the handling of the Origin header on incoming connections. An attacker can bypass access restrictions by exploiting DNS rebinding techniques, potentially gaining unauthorized access to server resources...

EUVD-2026-36608

OpenClaw before 2026.5.12 contains an exec denylist bypass vulnerability in the bundle MCP loopback session-spawn path that allows authenticated callers to bypass intended command restrictions. Attackers can reach the affected bundled MCP session-spawn path to start sessions with broader command...

CVE-2026-53820 OpenClaw < 2026.5.12 - Exec Denylist Bypass in Bundle MCP Loopback Session Spawn

OpenClaw before 2026.5.12 contains an exec denylist bypass vulnerability in the bundle MCP loopback session-spawn path that allows authenticated callers to bypass intended command restrictions. Attackers can reach the affected bundled MCP session-spawn path to start sessions with broader command...

CVE-2026-53820

OpenClaw contains an exec denylist bypass in the bundle MCP loopback session-spawn path prior to version 2026.5.12. This allows authenticated callers to bypass command restrictions and initiate sessions with broader command reach than intended. Affected component: bundle MCP session-spawn; root c...

CVE-2026-50287

AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCPHTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can...

CVE-2026-50287

AgenticMail MCP HTTP mode (via --http or MCP_HTTP=1) exposed the /mcp endpoint without HTTP authentication, enabling an unauthenticated remote client to initialize a session and call master-key tools. Affected component: @agenticmail/mcp; impact includes potential exposure of administrative/gatew...

CVE-2026-50287 Missing Authentication for Critical Function in @agenticmail/mcp

AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCPHTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can...

CVE-2026-53818 OpenClaw < 2026.4.24 - Owner-Only Tool Policy Bypass via MCP Loopback

OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools...

CVE-2026-53818

OpenClaw CVE-2026-53818 affects OpenClaw prior to 2026.4.24. It describes an authorization bypass in the MCP loopback feature that lets non-owner callers skip owner-only tool policies and before-tool-call hooks, potentially causing invocation of owner-only behavior to execute restricted tools whe...

CVE-2026-47250

mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Prior to version 3.7.0, the kubectlgeneric tool in mcp-server-kubernetes passes user-supplied flags directly to kubectl without any allowlist, enabling a privilege escalation attack within Kubernetes...

CVE-2026-46519

mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Prior to version 3.6.0, mcp-server-kubernetes exposes three environment variables ALLOWONLYREADONLYTOOLS, ALLOWONLYNONDESTRUCTIVETOOLS, ALLOWEDTOOLS documented as access controls for restricting which...

CVE-2026-47250

CVE-2026-47250 concerns mcp-server-kubernetes, where the kubectl_generic tool exposes a flag-injection vulnerability due to passing user-supplied flags directly to kubectl without an allowlist. This can enable a privilege-escalation path in Kubernetes environments: an attacker with limited access...

CVE-2026-47250 mcp-server-kubernetes: kubectl-generic flag injection enables Kubernetes bearer token exfiltration

mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Prior to version 3.7.0, the kubectlgeneric tool in mcp-server-kubernetes passes user-supplied flags directly to kubectl without any allowlist, enabling a privilege escalation attack within Kubernetes...

EUVD-2026-36287

mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Prior to version 3.7.0, the kubectlgeneric tool in mcp-server-kubernetes passes user-supplied flags directly to kubectl without any allowlist, enabling a privilege escalation attack within Kubernetes...