MCP Server (Preview)

Preview

This integration is in Preview mode and is not covered by the Syntasso SLA. If you are evaluating or using it, contact Syntasso to discuss applicability and expectations.

Overview

The Kratix MCP Server exposes your Kratix platform capabilities (browsing Promises, checking Destinations, and submitting requests) to AI agents over the Model Context Protocol.

This server is included in both SKE (Syntasso Kratix Enterprise) and SKA (Syntasso Kratix Agentic).

When you invest in Promises as your platform's standard API, you want your users' AI clients to discover and use those capabilities immediately. The Kratix MCP Server runs inside your cluster, connects to your platform's Promises, and makes them accessible in a secure, standard way to any MCP-compatible AI client.

Platform teams deploy the server once. Users register it with their AI client of choice and start asking questions about the platform from inside their editor.

Prerequisites

To get started, you will need a Syntasso registry token. You can request a token via the Syntasso website by clicking the "Try SKE Today" button.

In addition:

• An MCP-compatible AI client installed on user machines (see Connecting users for examples)
• A Kubernetes cluster running Kratix
• The published server image at ghcr.io/syntasso/ske-mcp-server:latest

Deploying the server

The server must run on the same cluster as Kratix, where it can reach the Kratix API resources directly. It deploys into the kratix-platform-system namespace alongside the Kratix platform components.

Apply the manifests from the release and create the auth secret:

kubectl apply -f deploy/kubernetes/
kubectl create secret generic ske-mcp-server-auth \
  --namespace kratix-platform-system \
  --from-literal=token="$(openssl rand -hex 32)"

The server exposes a Streamable HTTP endpoint at /mcp, protected by a shared bearer token. Requests are attributed per user via the X-User-Identity header.

Connecting users

The server uses Streamable HTTP transport, which any MCP-compatible AI client can connect to. The platform team should distribute a ready-to-run command with <SERVER_URL> and <TOKEN> already substituted; users should not need to look these up themselves. Consult your client's documentation for full MCP registration instructions. Below are examples for three popular clients.

Claude Code

claude mcp add --scope user --transport http ske-mcp-server <SERVER_URL>/mcp \
  --header "Authorization: Bearer <TOKEN>" \
  --header "X-User-Identity: $(whoami)"

See the Claude Code MCP docs for more options.

Cursor

Add the following to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "ske-mcp-server": {
      "url": "<SERVER_URL>/mcp",
      "headers": {
        "Authorization": "Bearer <TOKEN>",
        "X-User-Identity": "your-username"
      }
    }
  }
}

See the Cursor MCP docs for more options.

GitHub Copilot in VS Code

Add the following to .vscode/mcp.json in your workspace, or to your user settings:

{
  "servers": {
    "ske-mcp-server": {
      "type": "http",
      "url": "<SERVER_URL>/mcp",
      "headers": {
        "Authorization": "Bearer <TOKEN>",
        "X-User-Identity": "your-username"
      }
    }
  }
}

See the VS Code MCP docs for more options.

Querying your platform

Once connected, users can ask natural language questions about the platform directly in their AI client:

• What can I request from my platform?
• What destinations can I deploy my <Promise type> to?
• I need a <Promise type>. What can I configure?
• What's the status of my <request name> request?

The server provides the AI agent with the tools to answer these questions and, when the user is ready, submit a validated request through the platform's Promise workflows.

Available tools

Tool	What it does
fetch_promises	List available Promises
describe_promise_requestable	Promise summary, schema, and submit hints in one view
fetch_ready_destinations	Destinations that can accept requests
fetch_destination_contexts	Which destinations match a Promise's placement selectors
fetch_full_promises	Promises expanded with their matching resource instances
fetch_promise_requests	Requests scoped to a single Promise
get_request_status	Look up a single request by name and namespace
validate_promise_request	OpenAPI-schema preflight check before submitting
submit_promise_request	Create a namespaced request; stamps the requesting user and emits a Kubernetes Event

Debugging the server

To inspect the server interactively independent of any AI client, use the MCP Inspector. Configure it with:

Field	Value
Transport	Streamable HTTP
URL	<SERVER_URL>/mcp
Header	Authorization: Bearer <MCP_AUTH_TOKEN>