CVE-2026-44284
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- Low
- Integrity
- Low
- Availability
- Low
Exploit likelihood
What each source reports
CVE List Score used
6.3
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
- Record
CVE-2026-44284- CVSS 3.1
- 6.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L - Weakness
- CWE-918
- Updated
- 2026-11-02
EUVDEUVD-2026-28867
6.3
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
- Record
EUVD-2026-28867- CVSS 3.1
- 6.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L - Updated
- 2026-11-02
NVD
6.3
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
- Record
CVE-2026-44284- CVSS 3.1
- 6.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L - Weakness
- CWE-918
- Updated
- 2026-11-02
OSV
6.3
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
- Record
CVE-2026-44284- CVSS 3.1
- 6.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L - Weakness
- CWE-918
- Updated
- 2026-11-02
Affected products
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-44284 is a medium vulnerability (CVSS 6.3) in Labring Fastgpt, published May 8, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.24%, the 14th percentile. No source names a fixed version.
References
github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq
github.com/labring/FastGPT/pull/6826
github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69
github.com/labring/FastGPT/releases/tag/v4.14.17
github.com/CVEProject/cvelistV5/tree/main/cves/2026/44xxx/CVE-2026-44284.json
nvd.nist.gov/vuln/detail/CVE-2026-44284