CVE-2026-39974: n8n-MCP is a Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and oper...

Description

n8n-MCP is a Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTH_TOKEN to cause the server to issue HTTP requests to arbitrary URLs supplied through multi-tenant HTTP headers. Response bodies are reflected back through JSON-RPC, so an attacker can read the contents of any URL the server can reach — including cloud instance metadata endpoints (AWS IMDS, GCP, Azure, Alibaba, Oracle), internal network services, and any other host the server process has network access to. The primary at-risk deployments are multi-tenant HTTP installations where more than one operator can present a valid AUTH_TOKEN, or where a token is shared with less-trusted clients. Single-tenant stdio deployments and HTTP deployments without multi-tenant headers are not affected. This vulnerability is fixed in 2.47.4.

Metrics

CVSS 3.1

8.5/10

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N

EPSS Probability

0.32%

23.3th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-918

Affected Software

Vendor	Product	Versions
N8n-Mcp	N8n-Mcp	< 2.47.4

References

Timeline

Published: Apr 9, 2026
Last Modified: Jun 17, 2026
Status: Analyzed

Frequently Asked Questions

What is CVE-2026-39974?

n8n-MCP is a Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTH_TOKEN to cause the server to issue HTTP requests to arbitrary URLs supplied through multi-tenant HTTP headers. Response bodies are reflected back through JSON-RPC, so an attacker can read the contents of any URL the server can reach — including cloud instance metadata endpoints (AWS IMDS, GCP, Azure, Alibaba, Oracle), internal network services, and any other host the server process has network access to. The primary at-risk deployments are multi-tenant HTTP installations where more than one operator can present a valid AUTH_TOKEN, or where a token is shared with less-trusted clients. Single-tenant stdio deployments and HTTP deployments without multi-tenant headers are not affected. This vulnerability is fixed in 2.47.4.

How severe is CVE-2026-39974?

CVE-2026-39974 has a CVSS score of 8.5/10 (HIGH severity). The EPSS model estimates a 0.32% probability of exploitation in the next 30 days.

How do I fix CVE-2026-39974?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.