CyberRota Analysis
AI-GeneratedThe Model Context Protocol server in mcp-searxng versions prior to 1.7.1 is vulnerable to an attack that allows unauthenticated network clients to exploit improperly validated URLs, potentially leading to unauthorized access to internal services and exposure of sensitive credentials. Attackers can leverage this flaw to connect to private, loopback, or cloud-metadata addresses, thereby enumerating internal hosts and compromising security. Organizations using affected versions should prioritize upgrading to version 1.7.1 to mitigate this high-severity vulnerability.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
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.