CVE-2026-54688
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.
Scoring
- Severity
- MEDIUM
- CVSS base score
- 6.5
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
- EPSS probability
- 0.36%
- CWE
- CWE-918
- Published
- 2026-09-15
- Last modified
- 2026-09-15
Affected products
- ihor-sokoliuk mcp-searxng
Weakness type
Related vulnerabilities
- CVE-2026-83548 — A Pre-authentication SSRF vulnerability exists in the SMA1000 Appliance Work Place interface due to an unintended altern
- CVE-2026-87595 — Server-side request forgery in Mobile in Google Chrome prior to 153.0.8010.36 allowed a remote attacker leveraging socia
- CVE-2026-66842 — BIG-IP and BIG-IQ Configuration utility vulnerability
- CVE-2026-92808 — Server-Side Request Forgery in Altium Enterprise Server UnifiedLogin Service Allows Unauthenticated System Compromise
- CVE-2026-75754 — Missing Authentication for Critical Function, Server-Side Request Forgery (SSRF), and Use of Hard-coded Credentials in A
- CVE-2026-61559 — @zereight/mcp-gitlab Vulnerable to Server-Side Request Forgery
- CVE-2026-12944 — Incomplete Security Scanner Blocklist Enables Network-Based Code Execution
- CVE-2026-86123 — SQL Chat Unauthenticated Database-Connection Proxy in the /api/connection Endpoints