Authenticated internal network access via stored MCP URLs
Published May 8, 2026 · Updated May 8, 2026
Server-side request forgery in FastGPT before 4.14.17 allows remote authenticated users to reach internal services through MCP workflows. The MCP tool create and update handlers persist internal URLs without applying isInternalAddress, and workflow dispatch constructs MCPClient instances from those stored URLs without revalidation. MCP toolset management permission is required; the resulting backend connection can expose or affect only services reachable from the FastGPT deployment.
Summary
What happened
Server-side request forgery in FastGPT before 4.14.17 allows remote authenticated users to reach internal services through MCP workflows. The MCP tool create and update handlers persist internal URLs without applying isInternalAddress, and workflow dispatch constructs MCPClient instances from those stored URLs without revalidation. MCP toolset management permission is required; the resulting backend connection can expose or affect only services reachable from the FastGPT deployment.
The record
- CVE
- CVE-2026-44284
- Published
- May 8, 2026
- Updated
- May 8, 2026
- Vendor
- Labring
- Product
- FastGPT
- Classifications
- CWE-918
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- May 8, 2026CVE publishedPublication date reported by the CVE source.
- May 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 4.14.17
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GitHub advisory proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo