MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server

An XSS flaw exists in the MCP Inspector local development tool when it renders a redirect URL returned by a remote MCP server. If the Inspector connects to an untrusted server, a crafted redirect can inject script into the Inspector context and, via the built-in proxy, be leveraged to trigger arbitrary command execution on the developer machine. Version 0.16.6 hardens URL handling/validation and prevents script execution. > Thank you to the following researchers for their reports and contributions: > * Raymond (Veria Labs) > * Gavin Zhong, <superboyzjc@gmail.com> & Shuyang Wang, <swang@obsidiansecurity.com>.

CVSS 4.0

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Severity from

GitHub (reviewed advisory)

Weakness

CWE-79, CWE-84, CWE-94

Also known as

CVE-2025-58444

• github.com/modelcontextprotocol/inspector/security/advisories/GHSA-g9hg-qhmf-q45m
• nvd.nist.gov/vuln/detail/CVE-2025-58444
• github.com/modelcontextprotocol/inspector/commit/650f3090d26344a672026b737d81586595bb1f60
• github.com/modelcontextprotocol/inspector
• www.npmjs.com/package/@modelcontextprotocol/inspector/v/0.16.6