Unverified50% confidenceOpinionExact time
MCP's security model assumes that servers are trustworthy, and this assumption is being broken by attack cases.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe attacker initially published a clean, normal MCP server to establish trust, and later planted malicious forwarding logic by adding a single line of code in a subsequent version update.77% similarVerifiedMCP 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.77% 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.76% similarUnverifiedCritics point out that an MCP Server with file system write permissions, once exploited by malicious tools, would present an attack surface harder to audit than traditional API integrations75% similarUnverifiedTreating a gateway as a security substitute that makes a deployment secure once deployed is one of the most common security misconceptions during the initial launch of MCP services.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018470API
curl https://kongchang.com/api/v1/knowledge/claims/1018470MCP
get_claim(id=1018470)