mcpsnoop

MCP용 Wireshark. AI 클라이언트와 MCP 서버 사이의 모든 실제 도구 호출을 터미널에서 실시간으로 보여주는 투명 프록시입니다. 문제점 공식 MCP Inspector는 자체 클라이언트로 연결되므로 사용자의 클라이언트Cursor, Claude Code, Codex가 서버에 실제로 보내는 내용을 볼 수 없습니다. 또한 요청이 도착하기를 기다리는 방식은 모델이 호출하지 않았거나 잘못된 인수로 호출한 경우를 표시할 수 없습니다. 도구가 조용히 호출되지 않거나, 기능이 일치하지 않거나, 호출이 그냥 멈추는 경우 로그를 뒤지고...

Malicious code in dx-chat-ai-client (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 6fe55043b26ce76d97d00a4b1f3c89c2f2dfd3c8256f36139e90939f8ee1f570 Any computer that has this package installed or running should be considered...

MAL-2025-5311 Malicious code in dx-chat-ai-client (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 6fe55043b26ce76d97d00a4b1f3c89c2f2dfd3c8256f36139e90939f8ee1f570 Any computer that has this package installed or running should be considered...

MAL-2025-3905 Malicious code in meta-ai-client (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 230f2c424df3ca5115f3d575ba5a15c46f2a591f9a8ed4ec503c6bb5490ea355 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malicious code in meta-ai-client (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 230f2c424df3ca5115f3d575ba5a15c46f2a591f9a8ed4ec503c6bb5490ea355 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Information Disclosure

aimeos/ai-client-html is vulnerable to Sensitive Information Exposure. The vulnerability is due to debug information revealing sensitive information from environment variables in error logs, allowing attackers to potentially access confidential data...