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.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
FastGPTto a version that resolves this vulnerability.Fixed in 4.14.17
Event History
Frequently Asked Questions
What is the severity of CVE-2026-44284?
CVE-2026-44284 is classified as a moderate severity vulnerability due to its potential for stored SSRF attacks in FastGPT workflows.
How do I fix CVE-2026-44284?
To fix CVE-2026-44284, upgrade FastGPT to version 4.14.17 or later to ensure consistent SSRF protection.
What type of vulnerability is CVE-2026-44284?
CVE-2026-44284 is a stored Server-Side Request Forgery (SSRF) vulnerability affecting the MCP tool URL handling in FastGPT.
What versions of FastGPT are affected by CVE-2026-44284?
FastGPT versions prior to 4.14.17 are affected by CVE-2026-44284.
What impact does CVE-2026-44284 have on FastGPT users?
CVE-2026-44284 allows attackers to potentially access internal/private network resources through insecure URL handling.