Home

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.

PUBLISHED Reserved 2026-03-25 | Published 2026-03-31 | Updated 2026-03-31 | Assigner GitHub_M




HIGH: 7.7CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N

Problem types

CWE-918: Server-Side Request Forgery (SSRF)

Product status

< 4.14.9.5
affected

References

github.com/...astGPT/security/advisories/GHSA-x9vj-5m4j-9mfv

github.com/labring/FastGPT/pull/6640

github.com/...ommit/bc7eae2ed61481a5e322208829be291faec58c00

github.com/labring/FastGPT/releases/tag/v4.14.9.5

cve.org (CVE-2026-34163)

nvd.nist.gov (CVE-2026-34163)

Download JSON