CVE-2026-34163
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.28%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 7.7 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- EPSS
- 0.28% probability · 21th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-918
- Affected
- fastgpt/fastgpt
- Source
- security-advisories@github.com
References
- https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00Patch
- https://github.com/labring/FastGPT/pull/6640Issue Tracking, Patch
- https://github.com/labring/FastGPT/releases/tag/v4.14.9.5Product, Release Notes
- https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfvExploit, Mitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.