x=hub

your toolset

    build deployment
    sign in

    Sezzlee Local LLM

    mcpkey · package
    io.github.sezzlee/llm · v0.1.3
    deploy just this

    Let a planning agent hand bounded language work to a local Ollama model.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    #!/usr/bin/env bash
# llm (io.github.sezzlee/llm), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-llm.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec npx -y supergateway@4 --stdio 'npx -y @sezzlee/[email protected]' --outputTransport streamableHttp --stateful --host 127.0.0.1 --port 8101 --streamableHttpPath /mcp --healthEndpoint /healthz

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

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e SEZZLEE_LLM_MODEL -e SEZZLEE_LLM_BASE_URL -e SEZZLEE_LLM_NUM_CTX -e SEZZLEE_LLM_TIMEOUT_MS -e SEZZLEE_LLM_KEEP_ALIVE -e SEZZLEE_LLM_ROOT -e SEZZLEE_LLM_OUTPUT_DIR node:22-alpine sh -c 'npx -y supergateway@4 --stdio '"'"'npx -y @sezzlee/[email protected]'"'"' --outputTransport streamableHttp --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T23:35:30+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:
  llm:
    image: node:22-alpine
    command:
    - sh
    - -c
    - npx -y supergateway@4 --stdio 'npx -y @sezzlee/[email protected]' --outputTransport streamableHttp --stateful
      --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
    ports:
    - 127.0.0.1:8101:8000
    volumes:
    - npm-cache:/root/.npm
    healthcheck:
      test:
      - CMD-SHELL
      - wget -qO- http://127.0.0.1:8000/healthz || exit 1
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 2m
    restart: unless-stopped
    environment:
      SEZZLEE_LLM_MODEL: ${SEZZLEE_LLM_MODEL}
      SEZZLEE_LLM_BASE_URL: ${SEZZLEE_LLM_BASE_URL}
      SEZZLEE_LLM_NUM_CTX: ${SEZZLEE_LLM_NUM_CTX}
      SEZZLEE_LLM_TIMEOUT_MS: ${SEZZLEE_LLM_TIMEOUT_MS}
      SEZZLEE_LLM_KEEP_ALIVE: ${SEZZLEE_LLM_KEEP_ALIVE}
      SEZZLEE_LLM_ROOT: ${SEZZLEE_LLM_ROOT}
      SEZZLEE_LLM_OUTPUT_DIR: ${SEZZLEE_LLM_OUTPUT_DIR}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T23:35:30+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: llm
  namespace: mcp
  labels: &id001
    app: llm
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: llm
        image: node:22-alpine
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: SEZZLEE_LLM_MODEL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_MODEL
        - name: SEZZLEE_LLM_BASE_URL
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_BASE_URL
        - name: SEZZLEE_LLM_NUM_CTX
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_NUM_CTX
        - name: SEZZLEE_LLM_TIMEOUT_MS
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_TIMEOUT_MS
        - name: SEZZLEE_LLM_KEEP_ALIVE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_KEEP_ALIVE
        - name: SEZZLEE_LLM_ROOT
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_ROOT
        - name: SEZZLEE_LLM_OUTPUT_DIR
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: SEZZLEE_LLM_OUTPUT_DIR
        command:
        - sh
        - -c
        - npx -y supergateway@4 --stdio 'npx -y @sezzlee/[email protected]' --outputTransport streamableHttp
          --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
        readinessProbe:
          httpGet:
            path: /healthz
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: llm
  namespace: mcp
spec:
  selector:
    app: llm
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T23:35:30+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:
  llm:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: llm
      image: node:22-alpine
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: SEZZLEE_LLM_MODEL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_MODEL
      - name: SEZZLEE_LLM_BASE_URL
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_BASE_URL
      - name: SEZZLEE_LLM_NUM_CTX
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_NUM_CTX
      - name: SEZZLEE_LLM_TIMEOUT_MS
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_TIMEOUT_MS
      - name: SEZZLEE_LLM_KEEP_ALIVE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_KEEP_ALIVE
      - name: SEZZLEE_LLM_ROOT
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_ROOT
      - name: SEZZLEE_LLM_OUTPUT_DIR
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: SEZZLEE_LLM_OUTPUT_DIR
      command:
      - sh
      - -c
      - npx -y supergateway@4 --stdio 'npx -y @sezzlee/[email protected]' --outputTransport streamableHttp
        --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
      readinessProbe:
        httpGet:
          path: /healthz
          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: SEZZLEE_LLM_MODEL, SEZZLEE_LLM_BASE_URL, SEZZLEE_LLM_NUM_CTX, SEZZLEE_LLM_TIMEOUT_MS, SEZZLEE_LLM_KEEP_ALIVE, SEZZLEE_LLM_ROOT, SEZZLEE_LLM_OUTPUT_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
    npx -y @sezzlee/[email protected]
# env: SEZZLEE_LLM_MODEL, SEZZLEE_LLM_BASE_URL, SEZZLEE_LLM_NUM_CTX, SEZZLEE_LLM_TIMEOUT_MS, SEZZLEE_LLM_KEEP_ALIVE, SEZZLEE_LLM_ROOT, SEZZLEE_LLM_OUTPUT_DIR
    {
  "mcpServers": {
    "llm": {
      "command": "npx",
      "args": [
        "-y",
        "@sezzlee/[email protected]"
      ],
      "env": {
        "SEZZLEE_LLM_MODEL": "${SEZZLEE_LLM_MODEL}",
        "SEZZLEE_LLM_BASE_URL": "${SEZZLEE_LLM_BASE_URL}",
        "SEZZLEE_LLM_NUM_CTX": "${SEZZLEE_LLM_NUM_CTX}",
        "SEZZLEE_LLM_TIMEOUT_MS": "${SEZZLEE_LLM_TIMEOUT_MS}",
        "SEZZLEE_LLM_KEEP_ALIVE": "${SEZZLEE_LLM_KEEP_ALIVE}",
        "SEZZLEE_LLM_ROOT": "${SEZZLEE_LLM_ROOT}",
        "SEZZLEE_LLM_OUTPUT_DIR": "${SEZZLEE_LLM_OUTPUT_DIR}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add llm -e "SEZZLEE_LLM_MODEL=${SEZZLEE_LLM_MODEL}" -e "SEZZLEE_LLM_BASE_URL=${SEZZLEE_LLM_BASE_URL}" -e "SEZZLEE_LLM_NUM_CTX=${SEZZLEE_LLM_NUM_CTX}" -e "SEZZLEE_LLM_TIMEOUT_MS=${SEZZLEE_LLM_TIMEOUT_MS}" -e "SEZZLEE_LLM_KEEP_ALIVE=${SEZZLEE_LLM_KEEP_ALIVE}" -e "SEZZLEE_LLM_ROOT=${SEZZLEE_LLM_ROOT}" -e "SEZZLEE_LLM_OUTPUT_DIR=${SEZZLEE_LLM_OUTPUT_DIR}" -- npx -y @sezzlee/[email protected]

    {
  "mcpServers": {
    "llm": {
      "command": "npx",
      "args": [
        "-y",
        "@sezzlee/[email protected]"
      ],
      "env": {
        "SEZZLEE_LLM_MODEL": "${SEZZLEE_LLM_MODEL}",
        "SEZZLEE_LLM_BASE_URL": "${SEZZLEE_LLM_BASE_URL}",
        "SEZZLEE_LLM_NUM_CTX": "${SEZZLEE_LLM_NUM_CTX}",
        "SEZZLEE_LLM_TIMEOUT_MS": "${SEZZLEE_LLM_TIMEOUT_MS}",
        "SEZZLEE_LLM_KEEP_ALIVE": "${SEZZLEE_LLM_KEEP_ALIVE}",
        "SEZZLEE_LLM_ROOT": "${SEZZLEE_LLM_ROOT}",
        "SEZZLEE_LLM_OUTPUT_DIR": "${SEZZLEE_LLM_OUTPUT_DIR}"
      }
    }
  }
}
    {
  "servers": {
    "llm": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@sezzlee/[email protected]"
      ],
      "env": {
        "SEZZLEE_LLM_MODEL": "${SEZZLEE_LLM_MODEL}",
        "SEZZLEE_LLM_BASE_URL": "${SEZZLEE_LLM_BASE_URL}",
        "SEZZLEE_LLM_NUM_CTX": "${SEZZLEE_LLM_NUM_CTX}",
        "SEZZLEE_LLM_TIMEOUT_MS": "${SEZZLEE_LLM_TIMEOUT_MS}",
        "SEZZLEE_LLM_KEEP_ALIVE": "${SEZZLEE_LLM_KEEP_ALIVE}",
        "SEZZLEE_LLM_ROOT": "${SEZZLEE_LLM_ROOT}",
        "SEZZLEE_LLM_OUTPUT_DIR": "${SEZZLEE_LLM_OUTPUT_DIR}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.sezzlee/llm
    • 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.