/Gartner · Apr 9, 2026
Gartner: MCP and agents drive AI security incidents
Gartner predicts that by 2028, 25% of enterprise generative AI applications will experience at least five minor security incidents per year, up from 9% in 2025.
What changes
According to Gartner, the jump comes from agents and MCP: the protocol was designed for fast, easy interoperability, not for security by default, so mistakes show up in normal use. By 2029 it expects 15% of those applications to have at least one major incident per year, up from 3% in 2025. The biggest risk sits in workflows where an agent accesses sensitive data, processes untrusted content and communicates externally at the same time: Gartner recommends treating that combination as a no-go zone.
How to implement it
Inventory the agents and MCP servers already in use at your company, sanctioned or not.
Set up a formal security review for each MCP use case and start with the low-risk ones.
Give each agent its own identity and narrowly scoped permissions instead of inheriting a user's.
Defend against prompt injection and review third-party MCP components like any other dependency.
Nubent's take
It matches the most common mistakes we see when teams connect agents: giving them a person's role, installing MCP servers like just another plugin, and letting a workflow read external email while it has access to customer data. The defense isn't to stop AI, but to limit what each agent can do and log every call.
More news
See allAWS·
API Gateway REST validates JWTs without Lambda
Amazon API Gateway REST APIs now have a native JWT authorizer: they validate tokens from any OpenID Connect or OAuth 2.0 provider without writing a Lambda authorizer.
- API Gateway
- Security
- Serverless
AWS·
Cost Optimization Hub now stops idle EC2
You can now stop idle EC2 instances straight from Cost Optimization Hub recommendations, without going to the EC2 console, and see up front what you lose and what keeps billing.
- FinOps
- Amazon EC2
AWS·
EKS Auto Mode now rightsizes Pods for you
Amazon EKS Auto Mode adds, in preview, an optimization that adjusts Pod CPU and memory requests based on actual usage, so the same workloads run on fewer or smaller instances.
- Amazon EKS
- Kubernetes
- FinOps
Next step
Should we implement it in your account?
We check whether it fits, how much work it takes and what risks it carries. 30 minutes with an engineer.