Intel

AIKIDO-2026-632017

@modelcontextprotocol/inspector-server is vulnerable to Server-Side Request Forgery (SSRF)

Server-Side Request Forgery (SSRF) Pre-CVE
Found by Aikido Intel before public disclosure or CVE publication.
Published Jul 20, 2026

61

Medium Risk

This Affects:

JS@modelcontextprotocol/inspector-server
0.21.2 - 0.22.0
Fixed in 1.0.0
Are you affected? Scan for Free

TL;DR

The Inspector's server-side /fetch proxy forwards client-supplied http/https URLs to fetch() without restricting the target address. A connected MCP server can advertise OAuth discovery or token endpoints that resolve to link-local or cloud-metadata addresses such as 169.254.169.254, causing the proxy to request them and return the response. When the proxy runs on a cloud host this can expose instance metadata and IAM credentials, and redirects from an allowed host into a blocked address were not re-validated. The fix resolves the target host, blocks link-local/cloud-metadata ranges including IPv4-mapped IPv6 forms, and re-validates every redirect hop, returning 403 for blocked targets.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range and you run the Inspector proxy where it can reach internal or cloud-metadata addresses and connect it to an untrusted MCP server.

Background info

@modelcontextprotocol/inspector-server is vulnerable to Server-Side Request Forgery (SSRF) in versions 0.21.2 - 0.22.0.

How to fix this

Upgrade the @modelcontextprotocol/inspector-server and/or the @modelcontextprotocol/inspector library to the patch version.

Are You Affected?

Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.

Free. No credit card required.

Aikido Platform