modelcontextprotocol/inspector · Security
MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server
- GHSA ID
- GHSA-g9hg-qhmf-q45m
- CVE ID
- CVE-2025-58444
- Severity
- high
- Published
- Updated
- CVSS v4
- 8.6 · 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
Description
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, [email protected] & Shuyang Wang, [email protected].
CWEs
- CWE-79 · Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting')
- CWE-84 · Improper Neutralization of Encoded URI Schemes in a Web Page
- CWE-94 · Improper Control of Generation of Code ('Code Injection')
References
- https://github.com/modelcontextprotocol/inspector/security/advisories/GHSA-g9hg-qhmf-q45m ↗
- https://github.com/modelcontextprotocol/inspector/commit/650f3090d26344a672026b737d81586595bb1f60 ↗
- https://nvd.nist.gov/vuln/detail/CVE-2025-58444 ↗
- https://www.npmjs.com/package/@modelcontextprotocol/inspector/v/0.16.6 ↗
- https://github.com/advisories/GHSA-g9hg-qhmf-q45m ↗