MCP Runtime deploys Model Context Protocol servers into your Kubernetes cluster, checks every tool call against access policy, and records each decision for audit. Agents, IDEs, and people reach your internal tools through one governed gateway.
A public preview runs at platform.mcpruntime.org. The same platform installs into your own cluster.
Keep your MCP connections running in the background. Add a platform profile, then install its connection in Cursor, Codex, Claude Code, or VS Code.
macOS 13 or later · Apple Silicon and Intel · bundled service CLI.
This is an unsigned preview. After unzipping and moving the app to Applications, macOS may require allowing it in System Settings → Privacy & Security. Open it and choose Install and start.
# macOS: CLI and desktop preview
curl -fsSL https://raw.githubusercontent.com/mcp-runtime/mcp-runtime/main/install.sh | sh -s -- --with-desktop
# macOS or Linux: CLI only
curl -fsSL https://raw.githubusercontent.com/mcp-runtime/mcp-runtime/main/install.sh | shThe optional app installs in ~/Applications; the CLI installs in
~/.local/bin. The installer checks release checksums and keeps
existing apps. CLI setup and Windows instructions.
MCP Runtime is a self-hosted Kubernetes control plane for internal MCP servers. It deploys and routes those servers, authorizes tool calls, expires or revokes access, and audits requests inside your cluster, next to the data and services the servers already use.
You decide who can call a tool such as delete_invoice, up to what
trust level, and for how long. Servers, grants, and sessions are Kubernetes
resources, and a gateway in each server pod enforces them on every call.
apiVersion: mcpruntime.org/v1alpha1
kind: MCPServer
metadata:
name: payments
spec:
image: registry.example.com/payments-mcp:v1.0.0
port: 8088
publicPathPrefix: payments
gateway:
enabled: true
analytics:
enabled: trueDeploy an MCP server the way you deploy any other service.
A Kubernetes-native control plane to install the stack, reconcile MCPServer resources, and keep deployments healthy.
Image and deployment workflows for publishing MCP servers into environments your platform team controls.
A governed gateway that brokers agent access, applies policy before tool calls run, and records what happened.
Deploy servers, apply access policy, route requests through the gateway, and inspect audit and traffic data from one place.
Define MCP servers once as Kubernetes CRDs. The operator handles services, rollouts, routes, and updates in a GitOps-friendly workflow.
Grants and sessions make consent, trust level, expiry, and revocation Kubernetes resources. A call is denied unless a grant and a session allow it.
platform.mcpruntime.org shows the platform UI as it looks after installation. Anyone can browse the preview catalog; signed-in users can publish servers to it.
Agent traffic goes through a gateway that checks policy before a tool runs.
See each MCP call with its policy decision, timing, tool name, and status in dashboards and the analytics API.
Every governed request is recorded for security review, incident response, and compliance workflows.
The control plane runs in mcp-platform. Audit and telemetry run in mcp-observability. MCP servers stay in their own namespaces. Registry, ingress, API, UI, Grafana, and Prometheus install with setup.
go build -o bin/mcp-runtime ./cmd/mcp-runtime
./bin/mcp-runtime bootstrap
./bin/mcp-runtime setup --test-mode
./bin/mcp-runtime status
After setup, publish an MCP server, grant an agent access, then connect Cursor, Codex, Claude Code, VS Code, or another MCP client with the client connection guide. On macOS, the Adapter app can install a saved profile into supported agents.
Expose internal tools to agents with controlled access, request inspection, and audit trails.
Give teams one place to publish, operate, govern, and inspect MCP servers.
Try the public preview, then install the same platform in your own cluster for your own servers.
Grant another team time-limited access with a trust ceiling, and revoke it with one field.
Give security and compliance teams a searchable history of every tool call.
Kubernetes 1.25 or later, on any distribution. Open source and self-hosted.
If you would rather not operate MCP Runtime yourself, we can host it for you on our infrastructure, or set it up and manage it in yours. Either way you get the same guardrails: deny-by-default tool policy, time-limited and revocable agent sessions, and an audit record of every tool call.
Email us with your use case and where you want it to run.
A dedicated MCP Runtime install that we run and maintain. You deploy servers and manage access; we handle the cluster, upgrades, and monitoring.
We install and manage MCP Runtime in your own Kubernetes cluster, so your MCP servers and their data stay on infrastructure you control.
We charge only what it costs to run and manage the platform, with no profit margin. We are looking for our first customers: the first few pay the infrastructure cost only.
Open the public platform to see the UI, or follow the install guide to run MCP Runtime in your own cluster.