Verified65% confidenceCautionExact time
Common anti-patterns for MCP servers include excessive authorization, lack of request source validation, hardcoding sensitive credentials on the server side, and insufficient filtering of instructions passed in by agents.
3
Sources
65%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMCP servers face requests driven by natural language, where the requests themselves have no cryptographically verifiable origin, making the confused deputy problem particularly acute in agent scenarios.79% similarUnverifiedConnecting an MCP Server to an external system often involves network requests, third-party credentials and remote data, and its security and trust boundary is noticeably wider than that of built-in tools.77% similarUnverifiedThe MCP specification requires that tool annotations be treated as untrusted unless the server is trusted.77% similarUnverifiedThe caller of an MCP server is a model that may be misled, injected or simply make mistakes, so the security design must achieve "even if it errs, the fragmenting consequences are small and visible."77% similarUnverifiedThe confused deputy problem is one of the MCP security risks: an MCP Server holding broad credentials performs operations on behalf of a user who should not have that permission.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978165API
curl https://kongchang.com/api/v1/knowledge/claims/978165MCP
get_claim(id=978165)