CVE-2026-34163: Server-Side Request Forgery via MCP Tools Endpoint in FastGPT
FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
FastGPT MCP tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool)to a version that resolves this vulnerability.Fixed in 4.14.9.5
Event History
Frequently Asked Questions
What is the severity of CVE-2026-34163?
CVE-2026-34163 is classified as a high-severity vulnerability due to its impact on unauthorized access and server-side request forgery.
How do I fix CVE-2026-34163?
To fix CVE-2026-34163, update FastGPT to version 4.14.9.5 or later, which addresses the vulnerability in the MCP tools endpoints.
What versions of FastGPT are affected by CVE-2026-34163?
FastGPT versions prior to 4.14.9.5 are affected by CVE-2026-34163.
What is the impact of CVE-2026-34163 on applications?
The impact of CVE-2026-34163 includes potential unauthorized access to server resources through server-side request forgery.
Is there a workaround for CVE-2026-34163 if I cannot update?
As of now, there is no recommended workaround for CVE-2026-34163; updating to the patched version is the only secure option.