What transport does the MCP server use?
It uses Streamable-HTTP.
@Kuadrant
Basic information
POC for setting up Kuadrant with a mcp server running in a K8s cluster
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"kuadrant-mcp-poc": {
"command": "docker",
"args": [
"build",
"-t",
"quay.io/${QUAY_USERNAME}/mcp-server-everything",
"https://github.com/modelcontextprotocol/servers.git#main",
"-f",
"src/everything/Dockerfile"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
kuadrant-mcp-poc is a proof-of-concept that deploys an MCP server with Streamable-HTTP capabilities on a Kubernetes cluster, integrating with Kuadrant for DNS, TLS, rate limiting, and authentication. It is built on the everything MCP server and targets developers testing Kuadrant with an MCP workflow.
After meeting prerequisites (a Kubernetes cluster with Kuadrant installed), set environment variables for AWS credentials, domain, and Quay username. Build and push a Docker image for the MCP server, apply Kubernetes manifests to create the server pod, gateway, TLS, DNS, auth, and rate-limit policies. Configure VSCode Copilot as the MCP client by adding an HTTP server entry with the gateway URL and API key header (e.g., "Authorization": "APIKEY IAMALICE"). Then interact with the server through Copilot’s agent mode.
everything MCP serverIt uses Streamable-HTTP.
A Kubernetes cluster, Kuadrant installed, AWS credentials for DNS access, a Quay account for image upload, and a root domain.
The server runs as a pod in the `mcp-server` namespace on the Kubernetes cluster.
Yes. The setup deploys Kuadrant AuthPolicy (with API keys) and RateLimitPolicy to enforce authentication and request rate limits.
No. MCP clients do not accept self-signed certificates, so a trusted certificate issuer (e.g., Let’s Encrypt) must be used.

Run advanced phishing, voice phishing, deepfake fraud simulations, and cybersecurity awareness training from your AI assistant.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Hindsight: Agent Memory That Learns
Comments