CVE-2026-34163
Server-Side Request Forgery via MCP Tools Endpoint in FastGPT
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.
INFO
Published Date :
March 31, 2026, 3:16 p.m.
Last Modified :
July 24, 2026, 9:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update FastGPT to version 4.14.9.5 or later.
- Verify the SSRF protection is enabled.
- Review internal network access controls.
Public PoC/Exploit Available at Github
CVE-2026-34163 has a 1 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-34163.
| URL | Resource |
|---|---|
| https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00 | Patch |
| https://github.com/labring/FastGPT/pull/6640 | Issue Tracking Patch |
| https://github.com/labring/FastGPT/releases/tag/v4.14.9.5 | Product Release Notes |
| https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv | Exploit Mitigation Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-34163 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-34163
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
The Project shares all information on MCP related CVE's published
mcp mcp-security mcp-cve
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-34163 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-34163 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Translated by [email protected]
Jul. 24, 2026
Action Type Old Value New Value Added Translation Title: FastGPT de labring, Description: FastGPT es una plataforma de creación de agentes de IA. Antes de la versión 4.14.9.5, los endpoints de herramientas MCP (Model Context Protocol) de FastGPT (/api/core/app/mcpTools/getTools y /api/core/app/mcpTools/runTool) aceptan un parámetro URL proporcionado por el usuario y realizan solicitudes HTTP del lado del servidor a este sin validar si la URL apunta a una dirección de red interna/privada. Aunque la aplicación tiene una función isInternalAddress() dedicada para la protección SSRF (utilizada en otros endpoints como el nodo de flujo de trabajo HTTP), los endpoints de herramientas MCP no llaman a esta función. Un atacante autenticado puede usar estos endpoints para escanear redes internas, acceder a servicios de metadatos en la nube e interactuar con servicios internos como MongoDB y Redis. Este problema ha sido parcheado en la versión 4.14.9.5. -
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'labring', 'product': 'FastGPT', 'versions': [{'status': 'affected', 'version': '< 4.14.9.5'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-34163', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-03-31T15:37:50.933430Z'} -
Initial Analysis by [email protected]
Apr. 01, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N Added CPE Configuration OR *cpe:2.3:a:fastgpt:fastgpt:*:*:*:*:*:*:*:* versions up to (excluding) 4.14.9.5 Added Reference Type GitHub, Inc.: https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00 Types: Patch Added Reference Type GitHub, Inc.: https://github.com/labring/FastGPT/pull/6640 Types: Issue Tracking, Patch Added Reference Type GitHub, Inc.: https://github.com/labring/FastGPT/releases/tag/v4.14.9.5 Types: Product, Release Notes Added Reference Type GitHub, Inc.: https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv Types: Exploit, Mitigation, Vendor Advisory -
New CVE Received by [email protected]
Mar. 31, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N Added CWE CWE-918 Added Reference https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00 Added Reference https://github.com/labring/FastGPT/pull/6640 Added Reference https://github.com/labring/FastGPT/releases/tag/v4.14.9.5 Added Reference https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv