CVE-2026-58485
mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG.
Impact
mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.7.1, 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 resolution. A public-looking attacker-controlled hostname that resolves to a private, loopback, link-local, or cloud-metadata address therefore passes the lexical check and causes the MCP server to connect to the internal destination. In the default HTTP configuration, an unauthenticated network client can use this path to read internal services, expose credentials or service tokens, and enumerate reachable internal hosts; in STDIO deployments, prompt-influenced tool selection can provide the malicious URL. Direct private IP literals are blocked, and MCP_HTTP_ALLOW_PRIVATE_URLS remains an explicit opt-out. This issue is fixed in version 1.7.1.
Affected packages
This record carries no package version data, so it cannot be matched against a dependency list automatically. Read the advisory and compare your version by hand.
Weakness classification
References
- NVD record
- CVE.org record
- https://github.com/ihor-sokoliuk/mcp-searxng/commit/14575eaaa46a21391477d2b68673858ba6b52bd6
- https://github.com/ihor-sokoliuk/mcp-searxng/pull/120
- https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.7.1
- https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-mrvx-jmjw-vggc