PT-2026-48540

Due to the combination of checking out PR head branches attacker-controlled, reading .mcp.json from the working directory via default setting sources, and unconditionally enabling all project MCP servers via enableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a...

CVE-2026-44653

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

Description-Code Inconsistency in Real-World MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol MCP has emerged as a critical standard empowering Large Language Models LLMs to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool...

CVE-2026-44653

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

Malicious code in @ornexus/neocortex (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector bb66a92e1a8c414ee0c8877998a9587b7c8a4be3b9b27b76d874329a87bec5dc On npm install -g @ornexus/neocortex, postinstall.js spawns install.sh or install.ps1 which, by default, runs an installcoderabbit step that fetches...

CVE-2026-7094

A vulnerability was determined in ShadowCloneLabs GlutamateMCPServers up to e2de73280b01e5d943593dd1aa2c01c5b9112f78. Affected by this issue is some unknown functionality of the file src/puppeteer/index.ts of the component puppeteernavigate. Executing a manipulation of the argument url can lead t...

CVE-2026-7094 ShadowCloneLabs GlutamateMCPServers puppeteer_navigate index.ts server-side request forgery

A vulnerability was determined in ShadowCloneLabs GlutamateMCPServers up to e2de73280b01e5d943593dd1aa2c01c5b9112f78. Affected by this issue is some unknown functionality of the file src/puppeteer/index.ts of the component puppeteernavigate. Executing a manipulation of the argument url can lead t...

CVE-2026-7094

A vulnerability was determined in ShadowCloneLabs GlutamateMCPServers up to e2de73280b01e5d943593dd1aa2c01c5b9112f78. Affected by this issue is some unknown functionality of the file src/puppeteer/index.ts of the component puppeteernavigate. Executing a manipulation of the argument url can lead t...

CVE-2026-30624

CVE-2026-30624 affects Agent Zero 0.9.8, in the External MCP Servers configuration feature. A JSON MCP configuration can include arbitrary command and args, which are executed when applied without sufficient validation. This can allow an attacker to run arbitrary OS commands with the Agent Zero p...

PT-2026-33072

Agent Zero 0.9.8 contains a remote code execution vulnerability in its External MCP Servers configuration feature. The application allows users to define MCP servers using a JSON configuration containing arbitrary command and args values. These values are executed by the application when the...

CVE-2026-39417

Affected software : MaxKB, specifically versions 2.7.1 and earlier. Vulnerability details : An incomplete fix for CVE-2025-53928 leaves a Remote Code Execution in the MCP node of the workflow engine. The fix only patched the path loading MCP config from the database; the else branch that loads mc...

CVE-2026-34742 Model Context Protocol Go SDK: DNS Rebinding Protection Disabled by Default for Servers Running on Localhost

The Go MCP SDK used Go's standard encoding/json. Prior to version 1.4.0, the Model Context Protocol MCP Go SDK does not enable DNS rebinding protection by default for HTTP-based servers. When an HTTP-based MCP server is run on localhost without authentication with StreamableHTTPHandler or...

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol MCP standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks...

LibreChat 信息泄露漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within one interface. Versions of LibreChat from 0.8.2-rc1 to 0.8.3-rc1 have a vulnerability related to information leakage. This...

Auditing MCP Servers for Over-Privileged Tool Capabilities

The Model Context Protocol MCP has emerged as a standard for connecting Large Language Models LLMs to external tools and data. However, MCP servers often expose privileged capabilities, such as file system access, network requests, and command execution that can be exploited if not properly...

CVE-2025-69196 FastMCP OAuth Proxy token reuse across MCP servers

FastMCP is the standard framework for building MCP applications. Prior to version 2.14.2, the server does not properly respect the resource parameter submitted by the client in the authorization and token request. Instead of issuing the token explicitly for the MCP server, the token is issued for...

CVE-2025-69196 FastMCP OAuth Proxy token reuse across MCP servers

FastMCP is the standard framework for building MCP applications. Prior to version 2.14.2, the server does not properly respect the resource parameter submitted by the client in the authorization and token request. Instead of issuing the token explicitly for the MCP server, the token is issued for...

GHSA-W5CR-2QHR-JQC5 Cloudflare Agents has a Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...

CVE-2026-1721

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...

CVE-2026-1721

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...