CVE-2026-7147
A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.base_url results in server-side request forgery. Remote exploitation of the attack is possible. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
View on NVDAnalysis
This is a server-side request forgery vulnerability in mcp-chat-studio, a niche tool for managing Model Context Protocol chat interfaces. While the exploit is public and allows remote attacks, the software is not widely used enough in the general developer community to justify a broad security alert.
Severity
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:LCWE-918EPSS
Technical description
A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.base_url results in server-side request forgery. Remote exploitation of the attack is possible. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.