Threat Intelligence Database

CVE-2026-108716 affects punkpeye mcp-remote versions 0.8.0 through 0.14.3 and involves cleartext transmission of sensitive information. The vulnerability occurs in the authorizeWithDeviceCode function, which sends client secrets and receives tokens without enforcing HTTPS. If device authorization and token endpoints use non-loopback HTTP URLs, attackers on the network path can intercept client secrets and access/refresh tokens. This vulnerability has a medium severity score of 6. No patch or remediation information is provided in the available data.

A vulnerability in geelen mcp-remote versions 0.1.18 through 0.1.38 allows a remote attacker to obtain sensitive information via the SSE transport eventSourceInit fetch wrapper. This issue is identified as CVE-2026-52001 and has a high severity rating with a CVSS score of 7.5. The vulnerability involves unauthorized information disclosure without requiring user interaction or privileges.

CVE-2026-52001 is a vulnerability in geelen mcp-remote versions 0.1.18 through 0.1.38 that allows a remote attacker to obtain sensitive information via the SSE transport eventSourceInit fetch wrapper. The vulnerability has a high severity with a CVSS score of 7.5, indicating it can be exploited remotely without privileges or user interaction to disclose confidential data.

An issue in geelen mcp-remote 0.1.16 through 0.1.38 allows a remote attacker to execute arbitrary code via the open() functions

An issue in geelen mcp-remote 0.1.16 through 0.1.38 allows a remote attacker to execute arbitrary code via the src/lib/utils.ts and the getServerUrlHash function

An issue in geelen mcp-remote 0.1.32 through 0.1.38 allows a remote attacker to obtain sensitive information via the src/lib/authorization-server-metadata.ts, src/lib/utils.ts components

mcp-remote versions 0.1.32 through 0.1.38 are vulnerable to Server-Side Request Forgery (SSRF) via the resource_metadata URL extracted from a remote MCP server's WWW-Authenticate header

CVE-2025-6514 is a critical OS command injection vulnerability in mcp-remote version 0.0.5. It arises when mcp-remote connects to untrusted MCP servers and processes crafted input from the authorization_endpoint response URL without proper sanitization. This flaw allows remote attackers to execute arbitrary OS commands with the privileges of the mcp-remote process. The vulnerability has a CVSS score of 9.6, indicating high impact on confidentiality, integrity, and availability. Exploitation requires user interaction but no privileges or authentication. No known exploits are currently reported in the wild. European organizations using mcp-remote 0.

CriticalVulnerabilityGermanyFranceNetherlands+4#cve#cve-2025-6514#cwe-78