Unverified50% confidenceOpinionExact time
Making MCP stateless does not directly eliminate security risks such as prompt injection, but rather shifts the security focus from protecting sessions to validating every request.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMCP tool annotations (such as read-only, destructive, idempotent, and open-world) are hints rather than guarantees, and applications should treat them as untrusted information unless the server itself is trusted.79% similarUnverifiedMCP itself is not a complete security system; secure deployment still requires authentication, fine-grained authorization, encryption, sandboxing, observability, and human approval for sensitive operations.75% similarPartially VerifiedOne of the security risks of MCP is prompt injection attacks, where malicious data sources may embed instructions in returned content to induce the model to perform unauthorized operations.74% similarUnverifiedMCP authorization mandates the use of PKCE (Proof Key for Code Exchange) to prevent authorization codes from being intercepted and exploited.72% similarUnverifiedAnnotation declarations on MCP servers have no enforcement validation mechanism at the protocol level, creating a supply-chain trust problem where an attacker can publish a malicious server claiming to be read-only while performing arbitrary write operations.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026311API
curl https://kongchang.com/api/v1/knowledge/claims/1026311MCP
get_claim(id=1026311)