Showroom Docs MCP Server

Quarkus MCP Server that indexes Red Hat product documentation and the "IA Development From Zero To Hero" workshop for OpenShift Lightspeed.

---

Project maintained by maximilianoPizarro Hosted on GitHub Pages — Theme by mattgraham

Showroom Docs MCP Server

Servidor MCP Quarkus para OpenShift Lightspeed
Documentacion inteligente al alcance de tu chat

English | Espanol

---

Que es?

Showroom Docs MCP Server es un servidor Model Context Protocol (MCP) construido con Quarkus que indexa y expone documentacion del workshop “IA Development From Zero To Hero” (Neuralbank) junto con un extracto parcial de documentacion oficial de 9 productos Red Hat, permitiendo que OpenShift Lightspeed responda preguntas basadas en ese contexto.

Nota: La documentacion de productos Red Hat incluida es un extracto parcial y puede no reflejar las ultimas actualizaciones. Red Hat publica actualizaciones de su documentacion oficial de forma frecuente. Consulte siempre docs.redhat.com para la informacion mas actual y completa.

Caracteristicas

• Busqueda inteligente por keywords en mas de 2.5 MB de documentacion oficial (PDFs de Red Hat)
• 4 MCP Tools expuestos via Streamable HTTP para integracion con OLS
• 46 documentos cubriendo el workshop + productos Red Hat + productos Developer
• Imagen de contenedor lista para deploy en OpenShift
• Helm chart para instalacion declarativa

Documentacion indexada

Fuente	Contenido
Workshop Neuralbank	Caso de negocio, agentes MCP, Golden Path, DevSpaces, Keycloak, Connectivity Link, MCP Inspector, Deploy, OpenTelemetry, RAG
OpenShift Service Mesh 3.3	About, Installing, Observability, Gateways, Updating
Connectivity Link 1.3	Discover, Install, Configure, Observe
Developer Hub 1.9	Install, Configure, Auth, GitHub, MCP Tools
OpenShift Lightspeed 1.0	Install, Configure, Operate, Troubleshoot
OpenShift Observability 1	Overview hub
OpenTelemetry 3.9	Install, Collector, Instrumentation
OpenShift Pipelines 1.21	Install, Pipelines as Code, CI/CD
API Management 1	Getting started, Administering
OpenShift AI Cloud Service 1	Data Science, Model Serving, Llama Stack

Pasos de instalacion

Paso 1: Agregar repositorio Helm e instalar

helm repo add showroom-docs-mcp \
  https://maximilianopizarro.github.io/showroom-docs-mcp/

helm repo update

helm install showroom-docs-mcp showroom-docs-mcp/showroom-docs-mcp \
  --namespace openshift-lightspeed \
  --create-namespace \
  --set image.pullPolicy=Always

Paso 2: Verificar que el pod este corriendo

oc get pods -n openshift-lightspeed -l app=showroom-docs-mcp
# Esperado: 1/1 Running

Paso 3: Crear credenciales LLM (si es necesario)

oc create secret generic ols-llm-credentials \
  -n openshift-lightspeed \
  --from-literal=apitoken=<tu-api-token>

Paso 4: Configurar OLSConfig

apiVersion: ols.openshift.io/v1alpha1
kind: OLSConfig
metadata:
  name: cluster
spec:
  featureGates:
    - MCPServer
  llm:
    providers:
      - credentialsSecretRef:
          name: ols-llm-credentials
        models:
          - name: llama-32-3b-instruct
            parameters:
              maxTokensForResponse: 8192
        name: red_hat_openshift_ai
        type: rhoai_vllm
        url: 'http://llama-32-3b-instruct-openai.my-first-model.svc.cluster.local/v1'
  mcpServers:
    - name: showroom-docs-mcp
      timeout: 10
      url: 'http://showroom-docs-mcp.openshift-lightspeed.svc.cluster.local:8080/mcp'
  ols:
    conversationCache:
      postgres:
        maxConnections: 2000
        sharedBuffers: 256MB
      type: postgres
    defaultModel: llama-32-3b-instruct
    defaultProvider: red_hat_openshift_ai
    deployment:
      api:
        replicas: 1
      console:
        replicas: 1
      dataCollector: {}
      database:
        replicas: 1
      llamaStack: {}
      mcpServer: {}
    logLevel: INFO
    userDataCollection: {}
  olsDataCollector:
    logLevel: INFO

Importante: Usa /mcp (Streamable HTTP), no /mcp/sse.

oc apply -f cluster-ols.yml

Paso 5: Verificar la integracion MCP

oc logs -n openshift-lightspeed deploy/lightspeed-app-server \
  -c lightspeed-service-api | grep "tools from MCP"

# Esperado:
# Loaded 4 tools from MCP server 'showroom-docs-mcp'

Paso 6: Probar con Lightspeed

Abri la consola web de OpenShift, hace clic en el icono de chat de Lightspeed, y pregunta sobre la documentacion indexada.

Preguntas de ejemplo para Lightspeed

Una vez desplegado, abri el chat de OpenShift Lightspeed y pregunta:

• “How do I install OpenShift Service Mesh 3.3?”
• “Explain the architecture of Red Hat Developer Hub”
• “What are the steps to deploy a model with OpenShift AI?”
• “How do I configure Connectivity Link gateway policies?”
• “What is the Neuralbank workshop about?”
• “How do I build an MCP agent with Quarkus?”
• “How do I set up Pipelines as Code with Tekton?”
• “How does OpenShift Lightspeed OLSConfig work?”
• “What is RAG and how does it work with vector databases?”

Guia de instalacion completa – Arquitectura – Configuracion OLSConfig