← AI agent vulnerabilities

CVE-2026-54688

mcp-searxng

6.5
Severity
Medium
Published
September 15, 2026
Last modified
September 30, 2026

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, web_url_read passes a caller-supplied URL to the server-side fetch path while assertUrlAllowed() in src/url-reader.ts runs only when MCP_HTTP_HARDEN is enabled, even though MCP_HTTP_HARDEN is disabled by default in src/http-security.ts. In the default configuration, an attacker who influences the URL selected by a user or AI agent can make the server fetch loopback, private-network, or cloud metadata endpoint resources and return their contents into the model context. file:// URLs remain rejected, and the separate DNS-resolution and redirect-validation bypasses are outside this record. This issue is fixed in version 1.2.0.

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

Weakness

References

CVE-2026-54688 on NVD

Listed in

MediumMCP serversServer-side request forgery

More mcp-searxng CVEs

Sep 15
CVE-2026-584857.1

Web_url_read receives its caller-controlled URL through src/index.ts and validates only the literal hostname in assertUrlAllowed() within src/url-reader.ts before undiciFetch() performs operating-system DNS…

Sep 15
CVE-2026-584837.5

Web_url_read in src/index.ts passes a caller-supplied URL to readUrlContent() in src/url-reader.ts, where checkContentLength() treats a missing Content-Length header as an inconclusive preflight and the…

Sep 15
CVE-2026-546896.3

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…