x=hub

your toolset

    build deployment
    sign in

    Pronunciation & Voice Coach

    mcpkey · package
    io.github.JuhongPark/pronunciation · v0.3.0
    deploy just this

    Local MCP voice coach with English pronunciation, grammar, and fluency feedback.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    # once, as root:
# as_mcp DIR COMMAND...: runs COMMAND as the mcp user in DIR, its home, sandboxed as the
# units are: a package's install scripts can write to DIR only, as the server later can
as_mcp() {
  local dir="$1"; shift
  systemd-run --quiet --wait --pipe --collect --uid=mcp --gid=mcp \
    -p WorkingDirectory="$dir" -p Environment=HOME="$dir" -p ReadWritePaths="$dir" \
    -p NoNewPrivileges=true -p ProtectSystem=strict -p ProtectHome=true -p PrivateTmp=true \
    -- "$@" </dev/null
}
install -d -m 0750 -o mcp -g mcp /var/lib/mcp/pronunciation
# pronunciation: its packages, installed whole before its unit starts (no session installs)
systemctl stop mcp-my-agent-pronunciation.service 2>/dev/null || true
as_mcp /var/lib/mcp/pronunciation uv tool install mcp-server-pronunciation==0.3.0
as_mcp /var/lib/mcp/pronunciation uv tool install mcp-proxy

#!/usr/bin/env bash
# pronunciation (io.github.JuhongPark/pronunciation), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-pronunciation.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 mcp-server-pronunciation==0.3.0

[Unit]
Description=MCP server pronunciation (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/pronunciation
WorkingDirectory=/var/lib/mcp/pronunciation
ExecStart=/opt/mcp/my-agent/bin/pronunciation.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/pronunciation

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e MCP_PRONUNCIATION_MODEL -e HF_HUB_CACHE -e MCP_PRONUNCIATION_PRELOAD -e MCP_PRONUNCIATION_AUDIO_RETENTION -e TORCH_HOME ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx mcp-server-pronunciation==0.3.0'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T16:56:20+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:
  pronunciation:
    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 mcp-server-pronunciation==0.3.0
    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:
      MCP_PRONUNCIATION_MODEL: ${MCP_PRONUNCIATION_MODEL}
      HF_HUB_CACHE: ${HF_HUB_CACHE}
      MCP_PRONUNCIATION_PRELOAD: ${MCP_PRONUNCIATION_PRELOAD}
      MCP_PRONUNCIATION_AUDIO_RETENTION: ${MCP_PRONUNCIATION_AUDIO_RETENTION}
      TORCH_HOME: ${TORCH_HOME}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T16:56:20+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: pronunciation
  namespace: mcp
  labels: &id001
    app: pronunciation
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: pronunciation
        image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: MCP_PRONUNCIATION_MODEL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_PRONUNCIATION_MODEL
        - name: HF_HUB_CACHE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: HF_HUB_CACHE
        - name: MCP_PRONUNCIATION_PRELOAD
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_PRONUNCIATION_PRELOAD
        - name: MCP_PRONUNCIATION_AUDIO_RETENTION
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_PRONUNCIATION_AUDIO_RETENTION
        - name: TORCH_HOME
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TORCH_HOME
        args:
        - sh
        - -c
        - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx mcp-server-pronunciation==0.3.0
        readinessProbe:
          httpGet:
            path: /status
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: pronunciation
  namespace: mcp
spec:
  selector:
    app: pronunciation
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T16:56:20+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:
  pronunciation:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: pronunciation
      image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: MCP_PRONUNCIATION_MODEL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_PRONUNCIATION_MODEL
      - name: HF_HUB_CACHE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: HF_HUB_CACHE
      - name: MCP_PRONUNCIATION_PRELOAD
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_PRONUNCIATION_PRELOAD
      - name: MCP_PRONUNCIATION_AUDIO_RETENTION
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_PRONUNCIATION_AUDIO_RETENTION
      - name: TORCH_HOME
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TORCH_HOME
      args:
      - sh
      - -c
      - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx mcp-server-pronunciation==0.3.0
      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: MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, TORCH_HOME. 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 mcp-server-pronunciation==0.3.0
# env: MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, TORCH_HOME
    {
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "${MCP_PRONUNCIATION_MODEL}",
        "HF_HUB_CACHE": "${HF_HUB_CACHE}",
        "MCP_PRONUNCIATION_PRELOAD": "${MCP_PRONUNCIATION_PRELOAD}",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "${MCP_PRONUNCIATION_AUDIO_RETENTION}",
        "TORCH_HOME": "${TORCH_HOME}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add pronunciation -e "MCP_PRONUNCIATION_MODEL=${MCP_PRONUNCIATION_MODEL}" -e "HF_HUB_CACHE=${HF_HUB_CACHE}" -e "MCP_PRONUNCIATION_PRELOAD=${MCP_PRONUNCIATION_PRELOAD}" -e "MCP_PRONUNCIATION_AUDIO_RETENTION=${MCP_PRONUNCIATION_AUDIO_RETENTION}" -e "TORCH_HOME=${TORCH_HOME}" -- uvx mcp-server-pronunciation==0.3.0

    {
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "${MCP_PRONUNCIATION_MODEL}",
        "HF_HUB_CACHE": "${HF_HUB_CACHE}",
        "MCP_PRONUNCIATION_PRELOAD": "${MCP_PRONUNCIATION_PRELOAD}",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "${MCP_PRONUNCIATION_AUDIO_RETENTION}",
        "TORCH_HOME": "${TORCH_HOME}"
      }
    }
  }
}
    {
  "servers": {
    "pronunciation": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "${MCP_PRONUNCIATION_MODEL}",
        "HF_HUB_CACHE": "${HF_HUB_CACHE}",
        "MCP_PRONUNCIATION_PRELOAD": "${MCP_PRONUNCIATION_PRELOAD}",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "${MCP_PRONUNCIATION_AUDIO_RETENTION}",
        "TORCH_HOME": "${TORCH_HOME}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.JuhongPark/pronunciation
    • 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.