Unverified50% confidenceEventExact time
Invariant Labs coined the term for MCP tool poisoning attacks in April 2025.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 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.65% similarUnverifiedAs of 2025, mainstream AI tools such as Cursor and Claude Desktop have joined the MCP ecosystem, and LangGraph provides native support through the langchain-mcp-adapters package.65% similarUnverified在MCP层可以注入恶意工具返回值、拦截审计Agent的工具调用、模拟工具失败等边界情况，使MCP层成为对抗测试的注入点与观测窗61% similarVerifiedMCP 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.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977555API
curl https://kongchang.com/api/v1/knowledge/claims/977555MCP
get_claim(id=977555)