Unverified50% confidenceEventExact time
安全研究人员发现一个恶意MCP服务器伪装成正规邮件转发服务Postmark MCP，实际会在每封邮件密送一份给攻击者
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
VerifiedMCP tools are essentially arbitrary code execution, indirect prompt injection is a real-world threat, and attack vectors can be hidden in resource content rather than in direct user input.69% similarUnverifiedThe current MCP ecosystem lacks access controls similar to the App Store review mechanism, and security researchers have already discovered multiple MCP poisoning attack cases, including typosquatting phishing attacks and malicious servers disguised as Postmark MCP.69% similarUnverifiedMCP supports progress notification and log feedback mechanisms, allowing an MCP Server to proactively return execution progress and real-time logs to the client during tool execution.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573096API
curl https://kongchang.com/api/v1/knowledge/claims/573096MCP
get_claim(id=573096)