CVE-2026-34163: Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

Severity: high (CVSS 7.7 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.3% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-03-31 · updated 2026-07-24
Weakness: CWE-918

Description

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 products

labring FastGPT: before 4.14.9.5 — fixed in 4.14.9.5

How to fix

Upgrade to a fixed version: labring FastGPT 4.14.9.5. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-34163 or the next vulnerability affects your stack