Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · MCP Inspector

CVE-2025-58444: MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server

highCVSS 4.0 8.6GHSA-g9hg-qhmf-q45m

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.

Published Sep 8, 2025 · Updated Sep 26, 2025

Affected packages

@modelcontextprotocol/inspector

Ecosystem
npm
Affected
< 0.16.6
Fixed in
0.16.6
Check
npm ls @modelcontextprotocol/inspector

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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, & Shuyang Wang, .

Credited to cai0duque.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More MCP Inspector vulnerabilities

All MCP Inspector entries