GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

BREW-MCP-INSPECTOR-CVE-2… (GHSA-G9HG-QHMF-Q45M)

Vulnerability from osv_homebrew – Published: 2026-08-13 17:13 – Updated: 2026-09-17 19:40 – Source website
VLAI
Summary
MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server
Details

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.

Severity
8.6 (High)
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
References
To clipboard 

{
  "affected": [
    {
      "ecosystem_specific": {
        "fix": "bump",
        "range_state": "fixed",
        "upstream_fixed_in": "0.16.6"
      },
      "package": {
        "ecosystem": "Homebrew",
        "name": "mcp-inspector",
        "purl": "pkg:brew/mcp-inspector"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.14.2"
            },
            {
              "fixed": "0.16.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "database_specific": {
    "confidence": "high",
    "source": "matched",
    "strategy": "registry",
    "upstream_evidence": [
      {
        "ecosystem": "npm",
        "key": "pkg:npm/%40modelcontextprotocol/inspector@2.6.0",
        "name": "@modelcontextprotocol/inspector",
        "strategy": "registry",
        "subject_version": "2.6.0"
      }
    ]
  },
  "details": "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.\n\n\u003e Thank you to the following researchers for their reports and contributions:\n\u003e * Raymond (Veria Labs)\n\u003e * Gavin Zhong, \u003csuperboyzjc@gmail.com\u003e \u0026 Shuyang Wang, \u003cswang@obsidiansecurity.com\u003e.",
  "id": "BREW-mcp-inspector-CVE-2025-58444",
  "modified": "2026-09-17T19:40:46Z",
  "published": "2026-08-13T17:13:13Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/modelcontextprotocol/inspector/security/advisories/GHSA-g9hg-qhmf-q45m"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-58444"
    },
    {
      "type": "WEB",
      "url": "https://github.com/modelcontextprotocol/inspector/commit/650f3090d26344a672026b737d81586595bb1f60"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/modelcontextprotocol/inspector"
    },
    {
      "type": "WEB",
      "url": "https://www.npmjs.com/package/@modelcontextprotocol/inspector/v/0.16.6"
    }
  ],
  "schema_version": "1.7.3",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server",
  "upstream": [
    "GHSA-g9hg-qhmf-q45m",
    "CVE-2025-58444"
  ]
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.


Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.