Unauthenticated code execution via exposed MCP action
Published May 2, 2026 · Updated May 2, 2026
Remote code execution in ChatGPTNextWeb NextChat 2.16.0 through 2.16.1 allows remote attackers to run OS commands via an MCP Server Action. The unauthenticated addMcpServer action accepts command and args values, persists them, and passes them to StdioClientTransport, which spawns a child process. Server-capable deployments expose the action even when MCP is disabled; static export builds are unaffected, and commands run with the server process account.
Summary
What happened
Remote code execution in ChatGPTNextWeb NextChat 2.16.0 through 2.16.1 allows remote attackers to run OS commands via an MCP Server Action. The unauthenticated addMcpServer action accepts command and args values, persists them, and passes them to StdioClientTransport, which spawns a child process. Server-capable deployments expose the action even when MCP is disabled; static export builds are unaffected, and commands run with the server process account.
The record
- CVE
- CVE-2026-7644
- Published
- May 2, 2026
- Updated
- May 2, 2026
- Vendor
- ChatGPTNextWeb
- Product
- NextChat
- Classifications
- CWE-266, CWE-285, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 2, 2026CVE publishedPublication date reported by the CVE source.
- May 2, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=2.16.0
- Affected versionversion=2.16.1
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- NextChat addMcpServer RCE proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo