CVE-2026-46341 Apify MCP server: Domain Allowlist Bypass in fetch-apify-docs via String Prefix Matching

The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.9.21, the fetch-apify-docs tool in src/tools/common/fetchapifydocs.ts validates allowlisted documentation domains with...

CVE-2026-46341 Apify MCP server: Domain Allowlist Bypass in fetch-apify-docs via String Prefix Matching

The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.9.21, the fetch-apify-docs tool in src/tools/common/fetchapifydocs.ts validates allowlisted documentation domains with...

CVE-2026-47751

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-30623

A flaw was found in LiteLLM. This vulnerability allows a remote attacker to execute arbitrary operating system commands on the host where LiteLLM is running. This is possible because the application's MCP server creation functionality processes JSON configurations that can include unvalidated...

EUVD-2026-44846

LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality. The application allows users to add MCP servers via a JSON configuration specifying arbitrary command and args values. LiteLLM executes these values on the host without validation, enabling...

Improper Authorization

n8n-mcp is vulnerable to Improper Authorization. The vulnerability is due to insufficient tenant isolation in multi-tenant HTTP mode, which allows an authenticated tenant to access locally stored workflow version backups outside of its assigned tenant scope...

Improper Authorization

n8n-mcp is vulnerable to Improper Authorization. The vulnerability is due to insufficient tenant isolation of locally stored workflow version history, which allows an authenticated tenant to read or delete workflow backups belonging to other tenants, exposing sensitive configuration data and...

CVE-2026-62312 9Router: Authenticated RCE via Unvalidated MCP Plugin Arguments

9Router is an AI router & token saver. Prior to 0.5.2, 9Router allows a remote authenticated attacker to achieve arbitrary code execution on the host operating system by combining a Host header bypass of localhost-only routes with unvalidated MCP plugin args passed to childprocess.spawn, allowing...

CVE-2026-62312 9Router: Authenticated RCE via Unvalidated MCP Plugin Arguments

9Router is an AI router & token saver. Prior to 0.5.2, 9Router allows a remote authenticated attacker to achieve arbitrary code execution on the host operating system by combining a Host header bypass of localhost-only routes with unvalidated MCP plugin args passed to childprocess.spawn, allowing...

CVE-2026-49353 9Router: Local-Only Access Gate Bypass in 9router via Host Header SpoofING

9Router is an AI router & token saver. In 0.4.45 and earlier, 9Router's src/dashboardGuard.js local-only access gate used Host and Origin headers in isLocalRequest to protect /api/mcp/, /api/tunnel/, and /api/cli-tools/, allowing header spoofing in reverse proxy or tunnel deployments to reach MCP...

CVE-2026-55608

n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to 2.57.4, multi-tenant HTTP mode with ENABLEMULTITENANT=true could allow an authenticated tenant to access default-scope workflowversions backups instead of being confined to...

CVE-2026-55608

n8n-mcp prior to 2.57.4 is affected. In multi-tenant HTTP mode (ENABLE_MULTI_TENANT=true), an authenticated MCP HTTP tenant could access default-scope workflow_versions backups rather than its own tenant scope, potentially reading or deleting backups from prior single-tenant deployments or migrat...

CVE-2026-54052

n8n-MCP (HTTP mode with multi-tenancy enabled via ENABLE_MULTI_TENANT=true) is affected prior to version 2.56.1. An authenticated tenant could read and delete other tenants’ workflow version backups, including full node definitions, credential references, and authorization headers, due to backups...

CVE-2026-54052 n8n-MCP: Cross-tenant access to workflow version backups in multi-tenant HTTP deployments

n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to 2.56.1, in HTTP mode with multi-tenancy enabled through ENABLEMULTITENANT=true, n8n-mcp's local workflow version history backups were not isolated per tenant, allowing an...

CVE-2026-52870

The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol MCP. From 1.23.0 until 1.27.2, default handlers installed by server.experimental.enabletasks for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without recordin...

CVE-2026-59950

The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol MCP. Prior to 1.28.1, the deprecated mcp.server.websocket.websocketserver transport accepted WebSocket handshakes without applying Host or Origin header validation, leaving no SDK-level way to restric...

CVE-2026-59950

The MCP Python SDK (package name mcp on PyPI) contains a vulnerability in the deprecated mcp.server.websocket.websocket_server transport prior to version 1.28.1, which accepted WebSocket handshakes without Host or Origin header validation. This prevents restrictions on originating connections to ...

CVE-2026-52870

The MCP Python SDK (package mcp on PyPI) has a vulnerability in versions 1.23.0–1.27.1 where default handlers installed by server.experimental.enable_tasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel only operate on task identifiers and do not record the session that created each ...

CVE-2026-53512 Better Auth: OAuth refresh-token replay via missing client authentication on oidc-provider and mcp plugins

Better Auth is an authentication and authorization library for TypeScript. Prior to 1.6.11, the legacy oidcProvider and mcp plugins expose OAuth token endpoints whose refreshtoken grant authenticates only possession of the bound refreshToken row and matching clientid, without verifying the...