x=hub

your toolset

    build deployment
    sign in

    Spark SQL

    mcpkey · package
    io.github.aidancorrell/spark-sql-mcp-server · v0.1.2
    deploy just this

    Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    #!/usr/bin/env bash
# spark-sql (io.github.aidancorrell/spark-sql-mcp-server), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-spark-sql.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec uvx mcp-proxy --host 127.0.0.1 --port 8101 --pass-environment -- uvx spark-sql-mcp-server==0.1.2

[Unit]
Description=MCP server spark-sql (toolset my-agent), generated by Hub
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=mcp
Group=mcp
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/spark-sql
WorkingDirectory=/var/lib/mcp/spark-sql
ExecStart=/opt/mcp/my-agent/bin/spark-sql.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/spark-sql

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e SPARK_HOST -e SPARK_PORT -e SPARK_DATABASE -e SPARK_AUTH -e SPARK_USERNAME -e SPARK_PASSWORD -e SPARK_KERBEROS_SERVICE_NAME ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx spark-sql-mcp-server==0.1.2'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:12:33+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
#   cp .env.example .env    # fill the ${VAR}s
#   docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
  spark-sql:
    image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
    command:
    - sh
    - -c
    - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx spark-sql-mcp-server==0.1.2
    ports:
    - 127.0.0.1:8101:8000
    volumes:
    - uv-cache:/root/.cache/uv
    healthcheck:
      test:
      - CMD
      - python3
      - -c
      - import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/status')
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 2m
    restart: unless-stopped
    environment:
      SPARK_HOST: ${SPARK_HOST}
      SPARK_PORT: ${SPARK_PORT}
      SPARK_DATABASE: ${SPARK_DATABASE}
      SPARK_AUTH: ${SPARK_AUTH}
      SPARK_USERNAME: ${SPARK_USERNAME}
      SPARK_PASSWORD: ${SPARK_PASSWORD}
      SPARK_KERBEROS_SERVICE_NAME: ${SPARK_KERBEROS_SERVICE_NAME}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:12:33+00:00).
#   kubectl create namespace mcp
#   kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
#   kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
  name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: spark-sql
  namespace: mcp
  labels: &id001
    app: spark-sql
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: spark-sql
        image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: SPARK_HOST
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_HOST
        - name: SPARK_PORT
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_PORT
        - name: SPARK_DATABASE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_DATABASE
        - name: SPARK_AUTH
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_AUTH
        - name: SPARK_USERNAME
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_USERNAME
        - name: SPARK_PASSWORD
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_PASSWORD
        - name: SPARK_KERBEROS_SERVICE_NAME
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SPARK_KERBEROS_SERVICE_NAME
        command:
        - sh
        - -c
        - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx spark-sql-mcp-server==0.1.2
        readinessProbe:
          httpGet:
            path: /status
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: spark-sql
  namespace: mcp
spec:
  selector:
    app: spark-sql
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:12:33+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
  spark-sql:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: spark-sql
      image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: SPARK_HOST
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_HOST
      - name: SPARK_PORT
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_PORT
      - name: SPARK_DATABASE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_DATABASE
      - name: SPARK_AUTH
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_AUTH
      - name: SPARK_USERNAME
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_USERNAME
      - name: SPARK_PASSWORD
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_PASSWORD
      - name: SPARK_KERBEROS_SERVICE_NAME
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SPARK_KERBEROS_SERVICE_NAME
      command:
      - sh
      - -c
      - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx spark-sql-mcp-server==0.1.2
      readinessProbe:
        httpGet:
          path: /status
          port: http
        initialDelaySeconds: 10

# helm install my-agent helm/my-agent -n mcp

    in the cloud

    one click: the provider's deploy form opens filled in, in your own account
    koyeb
    deploy to koyeb

    The form opens with CHANGE_ME for each value you supply: SPARK_HOST, SPARK_PORT, SPARK_DATABASE, SPARK_AUTH, SPARK_USERNAME, SPARK_PASSWORD, SPARK_KERBEROS_SERVICE_NAME. Fill them in before you deploy.

    Clients connect to the service's https://…koyeb.app address plus /mcp.

    azure
    deploy to azuretemplate

    A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The portal asks for each value you supply as a secure parameter; the deployment's outputs list the endpoints.

    connect to it

    copy what your client needs
    uvx spark-sql-mcp-server==0.1.2
# env: SPARK_HOST, SPARK_PORT, SPARK_DATABASE, SPARK_AUTH, SPARK_USERNAME, SPARK_PASSWORD, SPARK_KERBEROS_SERVICE_NAME
    {
  "mcpServers": {
    "spark-sql": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "env": {
        "SPARK_HOST": "${SPARK_HOST}",
        "SPARK_PORT": "${SPARK_PORT}",
        "SPARK_DATABASE": "${SPARK_DATABASE}",
        "SPARK_AUTH": "${SPARK_AUTH}",
        "SPARK_USERNAME": "${SPARK_USERNAME}",
        "SPARK_PASSWORD": "${SPARK_PASSWORD}",
        "SPARK_KERBEROS_SERVICE_NAME": "${SPARK_KERBEROS_SERVICE_NAME}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add spark-sql -e "SPARK_HOST=${SPARK_HOST}" -e "SPARK_PORT=${SPARK_PORT}" -e "SPARK_DATABASE=${SPARK_DATABASE}" -e "SPARK_AUTH=${SPARK_AUTH}" -e "SPARK_USERNAME=${SPARK_USERNAME}" -e "SPARK_PASSWORD=${SPARK_PASSWORD}" -e "SPARK_KERBEROS_SERVICE_NAME=${SPARK_KERBEROS_SERVICE_NAME}" -- uvx spark-sql-mcp-server==0.1.2

    {
  "mcpServers": {
    "spark-sql": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "env": {
        "SPARK_HOST": "${SPARK_HOST}",
        "SPARK_PORT": "${SPARK_PORT}",
        "SPARK_DATABASE": "${SPARK_DATABASE}",
        "SPARK_AUTH": "${SPARK_AUTH}",
        "SPARK_USERNAME": "${SPARK_USERNAME}",
        "SPARK_PASSWORD": "${SPARK_PASSWORD}",
        "SPARK_KERBEROS_SERVICE_NAME": "${SPARK_KERBEROS_SERVICE_NAME}"
      }
    }
  }
}
    {
  "servers": {
    "spark-sql": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "env": {
        "SPARK_HOST": "${SPARK_HOST}",
        "SPARK_PORT": "${SPARK_PORT}",
        "SPARK_DATABASE": "${SPARK_DATABASE}",
        "SPARK_AUTH": "${SPARK_AUTH}",
        "SPARK_USERNAME": "${SPARK_USERNAME}",
        "SPARK_PASSWORD": "${SPARK_PASSWORD}",
        "SPARK_KERBEROS_SERVICE_NAME": "${SPARK_KERBEROS_SERVICE_NAME}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.aidancorrell/spark-sql-mcp-server
    • not probed yet: tools unpinned, ingest lists them

    tools

    Not probed yetThe tools appear once the hub or its worker has listed this entry. Running it still works: your client lists them on first start.