DEPLOY. SECURE. OPERATE.

MCP
control
plane.

Kavrynt helps platform teams register, operate, and route MCP servers for AI agents on Kubernetes. The Kavrynt Runtime installs in your cluster today as a signed beta; Kavrynt Cloud, the hosted control plane, is in development.

Run trial imagesRead docs
MCP · KUBERNETES · AI AGENTS · CONTROL PLANE
KAVRYNT CONTROL PLANE
MCPServerOperatorGateway
Declare MCP servers -> validate -> route agent traffic
THE PROBLEM

AI agents need MCP servers.
Teams need control.

THE KAVRYNT MVP

One Kubernetes path from manifest
to routed MCP traffic.

Teams declare an MCP server as a Kubernetes resource, the Operator validates it, and the Gateway routes agent traffic to it on any Kubernetes cluster. Kind is only the local test option.

● KUBERNETES CONTROL-PLANE PATHRUNNING
01 · INSTALLHelm chartINSTALLED
02 · INTENTMCPServerAPPLIED
03 · CONTROLOperatorVALIDATED
04 · STATUSReadyREADY
05 · DATA PLANEGatewayLOADED
06 · AGENTMCP TrafficROUTED
◆ KavryntMCPServer APIGateway routingKubernetes CRDHelm installKubernetes 1.29+
One resource. · One Gateway. · One Kubernetes-native control loop.
COMPONENTS

Small pieces with
clear responsibilities.

01

MCPServer

Kubernetes resource that declares an MCP server, validated at admission.

02

kavryctl

CLI for validating, registering, and inspecting MCP servers through your kubeconfig.

03

Gateway

Data-plane entry point that routes AI client traffic to MCP servers and never forwards caller credentials.

04

Operator

Kubernetes controller that validates MCPServer resources and reports readiness.

TRIAL IMAGES FOR KUBERNETES

Run Kavrynt on Kubernetes

Install the signed beta chart into your own cluster. Kind is useful when you want a disposable local cluster on your laptop.

# Local testing only
# kind create cluster --name kavrynt-trial

helm upgrade --install kavrynt oci://registry-1.docker.io/kavrynt/kavrynt \
  --version 0.0.2-beta.1 \
  --namespace kavrynt-system --create-namespace --wait

kubectl get deployments -n kavrynt-system
ARCHITECTURE

Runtime in your cluster,
control plane in the cloud.

MCP traffic never leaves your cluster. Kavrynt Cloud will receive inventory and usage metadata, not tool payloads.

01

Declare

Teams declare MCP servers as MCPServer resources with kubectl, GitOps, or kavryctl. The Operator validates them and reports readiness.

Available · beta
02

Route

The Gateway in your cluster routes AI client traffic to ready MCP servers from a read-only Kubernetes watch.

Available · beta
03

Govern

Kavrynt Cloud adds sign-in, cross-cluster inventory, MCP traffic visibility, and audit across clusters.

In development
COMMERCIAL TRIAL

Bring control
to MCP operations.

Kavrynt is ready for early MVP testing by developers who want to run MCP infrastructure on Kubernetes, from local Kind clusters to managed cloud clusters.

Start quickstartReview product docs