← Back to search

CVE-2026-79538

9.8 CRITICALpublic exploit available

Published 2026-09-29 · Updated 2026-09-29

AI risk analysis

Summary
The vulnerability allows for code execution via the internal MCP inspector proxy endpoint, posing a critical risk due to the high severity and potential for remote exploitation.
Exploitability
Exploitation is relatively straightforward given the public exploit references, requiring only access to the affected endpoint.
Blast radius
If exploited, this flaw could lead to full system compromise, allowing attackers to execute arbitrary code with high privileges.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to metatool-ai MetaMCP version 2.4.23 or later.
rcewebproxycode-execution

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio (createTransport, STDIO branch, routers/mcp-proxy/server.ts).

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Weaknesses

CWE-94

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.