x=hub

your toolset

    build deployment
    sign in

    Ticket AI

    mcpkey · package
    io.github.syrian963/ticket-ai-mcp · v0.1.1
    deploy just this

    Measures tickets against the ones your team already shipped: sections, length, labels, duplicates.

    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/ticket-ai
# ticket-ai: its packages, installed whole before its unit starts (no session installs)
systemctl stop mcp-my-agent-ticket-ai.service 2>/dev/null || true
as_mcp /var/lib/mcp/ticket-ai uv tool install ticket-ai-mcp==0.1.1
as_mcp /var/lib/mcp/ticket-ai uv tool install mcp-proxy

#!/usr/bin/env bash
# ticket-ai (io.github.syrian963/ticket-ai-mcp), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-ticket-ai.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 ticket-ai-mcp==0.1.1

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

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e TICKET_AI_TRACKER -e TICKET_AI_PROJECT -e TICKET_AI_GITLAB_URL -e TICKET_AI_GITLAB_TOKEN -e TICKET_AI_JIRA_URL -e TICKET_AI_JIRA_EMAIL -e TICKET_AI_JIRA_TOKEN -e TICKET_AI_GITHUB_TOKEN -e TICKET_AI_REPO -e TICKET_AI_TICKET_LANGUAGE -e TICKET_AI_CACHE_DIR ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx ticket-ai-mcp==0.1.1'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T20:44:17+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:
  ticket-ai:
    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 ticket-ai-mcp==0.1.1
    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:
      TICKET_AI_TRACKER: ${TICKET_AI_TRACKER}
      TICKET_AI_PROJECT: ${TICKET_AI_PROJECT}
      TICKET_AI_GITLAB_URL: ${TICKET_AI_GITLAB_URL}
      TICKET_AI_GITLAB_TOKEN: ${TICKET_AI_GITLAB_TOKEN}
      TICKET_AI_JIRA_URL: ${TICKET_AI_JIRA_URL}
      TICKET_AI_JIRA_EMAIL: ${TICKET_AI_JIRA_EMAIL}
      TICKET_AI_JIRA_TOKEN: ${TICKET_AI_JIRA_TOKEN}
      TICKET_AI_GITHUB_TOKEN: ${TICKET_AI_GITHUB_TOKEN}
      TICKET_AI_REPO: ${TICKET_AI_REPO}
      TICKET_AI_TICKET_LANGUAGE: ${TICKET_AI_TICKET_LANGUAGE}
      TICKET_AI_CACHE_DIR: ${TICKET_AI_CACHE_DIR}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T20:44:17+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: ticket-ai
  namespace: mcp
  labels: &id001
    app: ticket-ai
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: ticket-ai
        image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: TICKET_AI_TRACKER
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_TRACKER
        - name: TICKET_AI_PROJECT
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_PROJECT
        - name: TICKET_AI_GITLAB_URL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_GITLAB_URL
        - name: TICKET_AI_GITLAB_TOKEN
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_GITLAB_TOKEN
        - name: TICKET_AI_JIRA_URL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_JIRA_URL
        - name: TICKET_AI_JIRA_EMAIL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_JIRA_EMAIL
        - name: TICKET_AI_JIRA_TOKEN
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_JIRA_TOKEN
        - name: TICKET_AI_GITHUB_TOKEN
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_GITHUB_TOKEN
        - name: TICKET_AI_REPO
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_REPO
        - name: TICKET_AI_TICKET_LANGUAGE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_TICKET_LANGUAGE
        - name: TICKET_AI_CACHE_DIR
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: TICKET_AI_CACHE_DIR
        args:
        - sh
        - -c
        - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx ticket-ai-mcp==0.1.1
        readinessProbe:
          httpGet:
            path: /status
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: ticket-ai
  namespace: mcp
spec:
  selector:
    app: ticket-ai
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T20:44:17+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:
  ticket-ai:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: ticket-ai
      image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: TICKET_AI_TRACKER
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_TRACKER
      - name: TICKET_AI_PROJECT
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_PROJECT
      - name: TICKET_AI_GITLAB_URL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_GITLAB_URL
      - name: TICKET_AI_GITLAB_TOKEN
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_GITLAB_TOKEN
      - name: TICKET_AI_JIRA_URL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_JIRA_URL
      - name: TICKET_AI_JIRA_EMAIL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_JIRA_EMAIL
      - name: TICKET_AI_JIRA_TOKEN
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_JIRA_TOKEN
      - name: TICKET_AI_GITHUB_TOKEN
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_GITHUB_TOKEN
      - name: TICKET_AI_REPO
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_REPO
      - name: TICKET_AI_TICKET_LANGUAGE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_TICKET_LANGUAGE
      - name: TICKET_AI_CACHE_DIR
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: TICKET_AI_CACHE_DIR
      args:
      - sh
      - -c
      - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx ticket-ai-mcp==0.1.1
      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: TICKET_AI_TRACKER, TICKET_AI_PROJECT, TICKET_AI_GITLAB_URL, TICKET_AI_GITLAB_TOKEN, TICKET_AI_JIRA_URL, TICKET_AI_JIRA_EMAIL, TICKET_AI_JIRA_TOKEN, TICKET_AI_GITHUB_TOKEN, TICKET_AI_REPO, TICKET_AI_TICKET_LANGUAGE, TICKET_AI_CACHE_DIR. 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 ticket-ai-mcp==0.1.1
# env: TICKET_AI_TRACKER, TICKET_AI_PROJECT, TICKET_AI_GITLAB_URL, TICKET_AI_GITLAB_TOKEN, TICKET_AI_JIRA_URL, TICKET_AI_JIRA_EMAIL, TICKET_AI_JIRA_TOKEN, TICKET_AI_GITHUB_TOKEN, TICKET_AI_REPO, TICKET_AI_TICKET_LANGUAGE, TICKET_AI_CACHE_DIR
    {
  "mcpServers": {
    "ticket-ai": {
      "command": "uvx",
      "args": [
        "ticket-ai-mcp==0.1.1"
      ],
      "env": {
        "TICKET_AI_TRACKER": "${TICKET_AI_TRACKER}",
        "TICKET_AI_PROJECT": "${TICKET_AI_PROJECT}",
        "TICKET_AI_GITLAB_URL": "${TICKET_AI_GITLAB_URL}",
        "TICKET_AI_GITLAB_TOKEN": "${TICKET_AI_GITLAB_TOKEN}",
        "TICKET_AI_JIRA_URL": "${TICKET_AI_JIRA_URL}",
        "TICKET_AI_JIRA_EMAIL": "${TICKET_AI_JIRA_EMAIL}",
        "TICKET_AI_JIRA_TOKEN": "${TICKET_AI_JIRA_TOKEN}",
        "TICKET_AI_GITHUB_TOKEN": "${TICKET_AI_GITHUB_TOKEN}",
        "TICKET_AI_REPO": "${TICKET_AI_REPO}",
        "TICKET_AI_TICKET_LANGUAGE": "${TICKET_AI_TICKET_LANGUAGE}",
        "TICKET_AI_CACHE_DIR": "${TICKET_AI_CACHE_DIR}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add ticket-ai -e "TICKET_AI_TRACKER=${TICKET_AI_TRACKER}" -e "TICKET_AI_PROJECT=${TICKET_AI_PROJECT}" -e "TICKET_AI_GITLAB_URL=${TICKET_AI_GITLAB_URL}" -e "TICKET_AI_GITLAB_TOKEN=${TICKET_AI_GITLAB_TOKEN}" -e "TICKET_AI_JIRA_URL=${TICKET_AI_JIRA_URL}" -e "TICKET_AI_JIRA_EMAIL=${TICKET_AI_JIRA_EMAIL}" -e "TICKET_AI_JIRA_TOKEN=${TICKET_AI_JIRA_TOKEN}" -e "TICKET_AI_GITHUB_TOKEN=${TICKET_AI_GITHUB_TOKEN}" -e "TICKET_AI_REPO=${TICKET_AI_REPO}" -e "TICKET_AI_TICKET_LANGUAGE=${TICKET_AI_TICKET_LANGUAGE}" -e "TICKET_AI_CACHE_DIR=${TICKET_AI_CACHE_DIR}" -- uvx ticket-ai-mcp==0.1.1

    {
  "mcpServers": {
    "ticket-ai": {
      "command": "uvx",
      "args": [
        "ticket-ai-mcp==0.1.1"
      ],
      "env": {
        "TICKET_AI_TRACKER": "${TICKET_AI_TRACKER}",
        "TICKET_AI_PROJECT": "${TICKET_AI_PROJECT}",
        "TICKET_AI_GITLAB_URL": "${TICKET_AI_GITLAB_URL}",
        "TICKET_AI_GITLAB_TOKEN": "${TICKET_AI_GITLAB_TOKEN}",
        "TICKET_AI_JIRA_URL": "${TICKET_AI_JIRA_URL}",
        "TICKET_AI_JIRA_EMAIL": "${TICKET_AI_JIRA_EMAIL}",
        "TICKET_AI_JIRA_TOKEN": "${TICKET_AI_JIRA_TOKEN}",
        "TICKET_AI_GITHUB_TOKEN": "${TICKET_AI_GITHUB_TOKEN}",
        "TICKET_AI_REPO": "${TICKET_AI_REPO}",
        "TICKET_AI_TICKET_LANGUAGE": "${TICKET_AI_TICKET_LANGUAGE}",
        "TICKET_AI_CACHE_DIR": "${TICKET_AI_CACHE_DIR}"
      }
    }
  }
}
    {
  "servers": {
    "ticket-ai": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ticket-ai-mcp==0.1.1"
      ],
      "env": {
        "TICKET_AI_TRACKER": "${TICKET_AI_TRACKER}",
        "TICKET_AI_PROJECT": "${TICKET_AI_PROJECT}",
        "TICKET_AI_GITLAB_URL": "${TICKET_AI_GITLAB_URL}",
        "TICKET_AI_GITLAB_TOKEN": "${TICKET_AI_GITLAB_TOKEN}",
        "TICKET_AI_JIRA_URL": "${TICKET_AI_JIRA_URL}",
        "TICKET_AI_JIRA_EMAIL": "${TICKET_AI_JIRA_EMAIL}",
        "TICKET_AI_JIRA_TOKEN": "${TICKET_AI_JIRA_TOKEN}",
        "TICKET_AI_GITHUB_TOKEN": "${TICKET_AI_GITHUB_TOKEN}",
        "TICKET_AI_REPO": "${TICKET_AI_REPO}",
        "TICKET_AI_TICKET_LANGUAGE": "${TICKET_AI_TICKET_LANGUAGE}",
        "TICKET_AI_CACHE_DIR": "${TICKET_AI_CACHE_DIR}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.syrian963/ticket-ai-mcp
    • 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.