Become a Member

Regulation TrackerLaws, orders and treaties read for their security duties and clocks Standards & FrameworksAttack taxonomies, control catalogues and frontier frameworks AI Incident DatabaseThe security incident record, with mechanism and lesson Research Paper LibraryThe papers that define the field, summarised OSS DirectoryRed teaming, guardrail, supply chain and evaluation tools Case StudiesProgrammes built, with measured outcomes AI Vulnerability TrackerCVEs and advisories for the components AI systems are built from

Latest in the tracker

New York Stop Addictive Feeds Exploitation (SAFE) for Kids Act and implementing rulesNew York's law restricting algorithmic feeds for minors takes effect on 25 January 2027 under final rules published in July 2026, with certified age assurance and $5,000-per-violation penalties.

Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Become a Member

Home/AI Incident Database/mcp-remote OAuth proxy allows remote code execution from a malicious MCP server (CVE-2025-6514)

mcp-remote OAuth proxy allows remote code execution from a malicious MCP server (CVE-2025-6514)

JFrog found that connecting to an untrusted remote MCP server through the widely used mcp-remote proxy let the server execute arbitrary commands on the client machine, a critical flaw in core MCP infrastructure.

Severity: Highmcp-remotecve-2025-6514rce

Sources

jfrog.comhttps://jfrog.com/blog/2025-6514-critical-mcp-remote-rce-vulnerability/

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit incident Report a correction or request removal

mcp-remote OAuth proxy allows remote code execution from a malicious MCP server (CVE-2025-6514)

Sources

Contribute

Related in AI Incident Database

Malicious repository configuration executes when a coding agent opens the project (hooks injection, CVE-2025-59536)

Keras Lambda layers allow arbitrary code execution when loading untrusted models (CVE-2024-3660)