# CVE-2026-54689

## Summary

- **CVE ID:** CVE-2026-54689
- **Severity:** MEDIUM
- **CVSS Score:** 6.3 (CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N)
- **CWE:** CWE-200, CWE-918
- **Published:** Sep 15, 2026
- **Last Modified:** Sep 17, 2026

## Description

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.2.0, the web_url_read URL policy in src/url-reader.ts can be bypassed while MCP_HTTP_HARDEN is enabled and MCP_HTTP_ALLOW_PRIVATE_URLS is not enabled because redirect targets are not revalidated, 0.0.0.0 is not classified as an internal address, and IPv4-mapped IPv6 literals canonicalized to hexadecimal form are not recognized. These inputs allow an attacker-influenced tool call to make the MCP server fetch loopback or internal HTTP resources and return content from local services, private APIs, service-mesh endpoints, or cloud metadata endpoints. The separate hostname-to-private-address case addressed by the earlier partial fix is not part of these residual bypasses. This issue is fixed in version 1.2.0.

## Affected Products

- ihor-sokoliuk — mcp-searxng (< 1.2.0)

## References

- [CNA](https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6)
- [CNA](https://github.com/ihor-sokoliuk/mcp-searxng/pull/79)
- [CNA](https://github.com/ihor-sokoliuk/mcp-searxng/commit/48e5ecdcb4166a60b94c252dbe74b0a318110ac4)
- [CNA](https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.2.0)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.13%
- **EPSS Percentile:** 3.3

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-17._