CVE-2026-54689

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.

CVSS v3 6.3 MEDIUM

6.3^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 1.8 / Impact : 4.0

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact NONE

Availability Impact NONE

Scope CHANGED

References

Link	Resource
https://github.com/ihor-sokoliuk/mcp-searxng/commit/48e5ecdcb4166a60b94c252dbe74b0a318110ac4
https://github.com/ihor-sokoliuk/mcp-searxng/pull/79
https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.2.0
https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6

Configurations

No configuration.

History

No history.

Information

Published : 2026-09-15 18:17

Updated : 2026-09-15 18:17

NVD link : CVE-2026-54689

Mitre link : CVE-2026-54689

CVE.ORG link : CVE-2026-54689

JSON object : View

Products Affected

No product.

CWE

CWE-200

Exposure of Sensitive Information to an Unauthorized Actor

CWE-918

Server-Side Request Forgery (SSRF)

{"id": "CVE-2026-54689", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 6.3, "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 4.0, "exploitabilityScore": 1.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "ihor-sokoliuk", "product": "mcp-searxng", "versions": [{"status": "affected", "version": "< 1.2.0"}]}]}], "published": "2026-09-15T18:17:23.477", "references": [{"url": "https://github.com/ihor-sokoliuk/mcp-searxng/commit/48e5ecdcb4166a60b94c252dbe74b0a318110ac4", "source": "security-advisories@github.com"}, {"url": "https://github.com/ihor-sokoliuk/mcp-searxng/pull/79", "source": "security-advisories@github.com"}, {"url": "https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.2.0", "source": "security-advisories@github.com"}, {"url": "https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6", "source": "security-advisories@github.com"}], "vulnStatus": "Received", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-200"}, {"lang": "en", "value": "CWE-918"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2026-09-15T18:17:23.477", "sourceIdentifier": "security-advisories@github.com"}