x=hub

your toolset

    build deployment
    sign in

    agentor

    projectother official build verified dockerfile by the hub scanned
    io.github.celestoai/agentor · v
    deploy just this

    Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

    run it

    on your own machines, one way per deploy method
    verified 2026-10-17 · r-20261017T125451Z-cdbe2b01f240
    The repository has no Dockerfile that builds here: this build uses one the hub wrote (hub-llm:hub-coder@p5), which its worker built and ran, checked by hub-llm:gpt-oss:120b@r2.
    # once, as root:
    docker build -t mcp-local/agentor:cbc309171a20f79ca5783b79929652768aee0f38 -f - https://github.com/CelestoAI/agentor.git#cbc309171a20f79ca5783b79929652768aee0f38 <<'DOCKERFILE'
    FROM python:3.12.8-slim
    WORKDIR /app
    COPY . .
    RUN pip install .
    RUN useradd --create-home app
    USER app
    EXPOSE 8000
    CMD ["python", "-c", "from agentor.mcp.server import LiteMCP; server = LiteMCP(); server.serve(host='0.0.0.0', port=8000, enable_cors=False)"]
    DOCKERFILE
    
    #!/usr/bin/env bash
    # agentor (io.github.celestoai/agentor), recipe docker (worker, verified 2026-10-17 on v, run r-20261017T125451Z-cdbe2b01f240).
    # Generated by Hub for toolset "my-agent"; started by mcp-my-agent-agentor.service.
    set -euo pipefail
    export HOST=127.0.0.1 PORT=8101
    exec docker run --rm --name mcp-my-agent-agentor -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env mcp-local/agentor:cbc309171a20f79ca5783b79929652768aee0f38
    
    [Unit]
    Description=MCP server agentor (toolset my-agent), generated by Hub
    After=network-online.target docker.service
    Wants=network-online.target
    
    [Service]
    Type=simple
    User=mcp
    Group=mcp
    SupplementaryGroups=docker
    EnvironmentFile=/etc/mcp/my-agent.env
    Environment=HOME=/var/lib/mcp/agentor
    WorkingDirectory=/var/lib/mcp/agentor
    ExecStart=/opt/mcp/my-agent/bin/agentor.sh
    Restart=on-failure
    RestartSec=5
    NoNewPrivileges=true
    ProtectSystem=strict
    ProtectHome=true
    PrivateTmp=true
    ReadWritePaths=/var/lib/mcp/agentor
    
    [Install]
    WantedBy=multi-user.target
    
    verified 2026-10-17 · r-20261017T125451Z-cdbe2b01f240
    The repository has no Dockerfile that builds here: this build uses one the hub wrote (hub-llm:hub-coder@p5), which its worker built and ran, checked by hub-llm:gpt-oss:120b@r2.
    docker build -t agentor -f - https://github.com/CelestoAI/agentor.git#cbc309171a20f79ca5783b79929652768aee0f38 <<'DOCKERFILE'
    FROM python:3.12.8-slim
    WORKDIR /app
    COPY . .
    RUN pip install .
    RUN useradd --create-home app
    USER app
    EXPOSE 8000
    CMD ["python", "-c", "from agentor.mcp.server import LiteMCP; server = LiteMCP(); server.serve(host='0.0.0.0', port=8000, enable_cors=False)"]
    DOCKERFILE
    docker run --rm -p 127.0.0.1:8101:8000 agentor
    
    verified 2026-10-17 · r-20261017T125451Z-cdbe2b01f240
    The repository has no Dockerfile that builds here: this build uses one the hub wrote (hub-llm:hub-coder@p5), which its worker built and ran, checked by hub-llm:gpt-oss:120b@r2.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:14:05+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:
      agentor:
        build:
          context: https://github.com/CelestoAI/agentor.git#cbc309171a20f79ca5783b79929652768aee0f38
          dockerfile_inline: |
            FROM python:3.12.8-slim
            WORKDIR /app
            COPY . .
            RUN pip install .
            RUN useradd --create-home app
            USER app
            EXPOSE 8000
            CMD ["python", "-c", "from agentor.mcp.server import LiteMCP; server = LiteMCP(); server.serve(host='0.0.0.0', port=8000, enable_cors=False)"]
        x-dockerfile: written by the hub (hub-llm:hub-coder@p5), checked by hub-llm:gpt-oss:120b@r2, not taken
          from the repository
        ports:
        - 127.0.0.1:8101:8000
        restart: unless-stopped
    volumes:
      npm-cache: {}
      uv-cache: {}
    
    verified 2026-10-17 · r-20261017T125451Z-cdbe2b01f240
    The repository has no Dockerfile that builds here: this build uses one the hub wrote (hub-llm:hub-coder@p5), which its worker built and ran, checked by hub-llm:gpt-oss:120b@r2.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:14:05+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: agentor
      namespace: mcp
      labels: &id001
        app: agentor
    spec:
      replicas: 1
      selector:
        matchLabels: *id001
      template:
        metadata:
          labels: *id001
        spec:
          containers:
          - name: agentor
            image: CHANGE_ME
            ports:
            - containerPort: 8000
              name: http
            env: []
    ---
    apiVersion: v1
    kind: Service
    metadata:
      name: agentor
      namespace: mcp
    spec:
      selector:
        app: agentor
      ports:
      - port: 8000
        targetPort: http
        name: http
    
    dockerfile
    FROM python:3.12.8-slim
    WORKDIR /app
    COPY . .
    RUN pip install .
    RUN useradd --create-home app
    USER app
    EXPOSE 8000
    CMD ["python", "-c", "from agentor.mcp.server import LiteMCP; server = LiteMCP(); server.serve(host='0.0.0.0', port=8000, enable_cors=False)"]
    
    verified 2026-10-17 · r-20261017T125451Z-cdbe2b01f240
    The repository has no Dockerfile that builds here: this build uses one the hub wrote (hub-llm:hub-coder@p5), which its worker built and ran, checked by hub-llm:gpt-oss:120b@r2.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:14:05+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:
      agentor:
        enabled: true
        replicas: 1
        port: 8000
        path: /mcp
        container:
          name: agentor
          image: CHANGE_ME
          ports:
          - containerPort: 8000
            name: http
          env: []
    
    # helm install my-agent helm/my-agent -n mcp
    
    dockerfile
    FROM python:3.12.8-slim
    WORKDIR /app
    COPY . .
    RUN pip install .
    RUN useradd --create-home app
    USER app
    EXPOSE 8000
    CMD ["python", "-c", "from agentor.mcp.server import LiteMCP; server = LiteMCP(); server.serve(host='0.0.0.0', port=8000, enable_cors=False)"]
    

    Scanned github.com/celestoai/agentor at cbc309171a20 with [email protected][email protected] on 2026-10-17 before the build: 1 dependencies, 8 known vulnerabilities (4 high, 1 medium, 3 low), nothing in the code that looks malicious.

    connect to it

    copy what your client needs
    {
      "mcpServers": {
        "agentor": {
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    #!/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 agentor -- CHANGE_ME
    
    {
      "mcpServers": {
        "agentor": {
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    {
      "servers": {
        "agentor": {
          "type": "stdio",
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    name: my-agent
    target: local
    servers:
    - hub: io.github.celestoai/agentor
    
    • not probed yet: tools unpinned, ingest lists them
    • no tested recipe for target 'local' yet: build it from https://github.com/CelestoAI/agentor by hand, or wait for the worker

    tools

    Probe result: okThe hub could not list this entry; it is retried on the next probe run.

    runs · 2

    the latest tests of this entry by the hub and its workers, newest first
    dateworkermethodstatussandboxreason
    2026-10-17 12:54 local-mac-vm dockermcp 2025-11-25 ok gvisor —
    2026-10-17 12:33 local-mac-vm docker failed gvisor docker: sandbox: docker build: ERROR: failed to build: failed to solve: failed to read dockerfile: open Dockerfile: no such file or directory