x=hub

your toolset

    build deployment
    sign in

    Exec Sandbox

    mcpother
    io.github.inhuman/mcp-exec · v0.5.4
    deploy just this

    Single exec tool running caller Python in a network-isolated locked-down sandbox.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
    #!/usr/bin/env bash
# exec (io.github.inhuman/mcp-exec), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-exec.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-exec -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env docker.io/idconstruct/mcp-exec:v0.5.4

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

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
    docker run --rm -p 127.0.0.1:8101:8000 -e MCP_EXEC_TRANSPORT -e MCP_EXEC_DEFAULT_TIMEOUT_S -e MCP_EXEC_MAX_TIMEOUT_S -e MCP_EXEC_MAX_OUTPUT_BYTES -e MCP_EXEC_MAX_STDIN_BYTES -e MCP_EXEC_AUTH_TOKEN docker.io/idconstruct/mcp-exec:v0.5.4
    generated from the record, not tested yet
    CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:32:50+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:
  exec:
    image: docker.io/idconstruct/mcp-exec:v0.5.4
    ports:
    - 127.0.0.1:8101:8000
    restart: unless-stopped
    x-note: 'CHANGE_ME: check the image''s README for its transport and port; this assumes streamable
      HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command
      instead.'
    environment:
      MCP_EXEC_TRANSPORT: ${MCP_EXEC_TRANSPORT}
      MCP_EXEC_DEFAULT_TIMEOUT_S: ${MCP_EXEC_DEFAULT_TIMEOUT_S}
      MCP_EXEC_MAX_TIMEOUT_S: ${MCP_EXEC_MAX_TIMEOUT_S}
      MCP_EXEC_MAX_OUTPUT_BYTES: ${MCP_EXEC_MAX_OUTPUT_BYTES}
      MCP_EXEC_MAX_STDIN_BYTES: ${MCP_EXEC_MAX_STDIN_BYTES}
      MCP_EXEC_AUTH_TOKEN: ${MCP_EXEC_AUTH_TOKEN}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:32:50+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: exec
  namespace: mcp
  labels: &id001
    app: exec
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: exec
        image: docker.io/idconstruct/mcp-exec:v0.5.4
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: MCP_EXEC_TRANSPORT
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_TRANSPORT
        - name: MCP_EXEC_DEFAULT_TIMEOUT_S
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_DEFAULT_TIMEOUT_S
        - name: MCP_EXEC_MAX_TIMEOUT_S
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_MAX_TIMEOUT_S
        - name: MCP_EXEC_MAX_OUTPUT_BYTES
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_MAX_OUTPUT_BYTES
        - name: MCP_EXEC_MAX_STDIN_BYTES
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_MAX_STDIN_BYTES
        - name: MCP_EXEC_AUTH_TOKEN
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MCP_EXEC_AUTH_TOKEN
---
apiVersion: v1
kind: Service
metadata:
  name: exec
  namespace: mcp
spec:
  selector:
    app: exec
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
    # Generated by Hub for toolset "my-agent" (2026-10-18T03:32:50+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:
  exec:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: exec
      image: docker.io/idconstruct/mcp-exec:v0.5.4
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: MCP_EXEC_TRANSPORT
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_TRANSPORT
      - name: MCP_EXEC_DEFAULT_TIMEOUT_S
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_DEFAULT_TIMEOUT_S
      - name: MCP_EXEC_MAX_TIMEOUT_S
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_MAX_TIMEOUT_S
      - name: MCP_EXEC_MAX_OUTPUT_BYTES
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_MAX_OUTPUT_BYTES
      - name: MCP_EXEC_MAX_STDIN_BYTES
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_MAX_STDIN_BYTES
      - name: MCP_EXEC_AUTH_TOKEN
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MCP_EXEC_AUTH_TOKEN

# 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_EXEC_TRANSPORT, MCP_EXEC_DEFAULT_TIMEOUT_S, MCP_EXEC_MAX_TIMEOUT_S, MCP_EXEC_MAX_OUTPUT_BYTES, MCP_EXEC_MAX_STDIN_BYTES, MCP_EXEC_AUTH_TOKEN. 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
    docker run -i --rm -e MCP_EXEC_TRANSPORT -e MCP_EXEC_DEFAULT_TIMEOUT_S -e MCP_EXEC_MAX_TIMEOUT_S -e MCP_EXEC_MAX_OUTPUT_BYTES -e MCP_EXEC_MAX_STDIN_BYTES -e MCP_EXEC_AUTH_TOKEN docker.io/idconstruct/mcp-exec:v0.5.4
    {
  "mcpServers": {
    "exec": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_EXEC_TRANSPORT",
        "-e",
        "MCP_EXEC_DEFAULT_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_OUTPUT_BYTES",
        "-e",
        "MCP_EXEC_MAX_STDIN_BYTES",
        "-e",
        "MCP_EXEC_AUTH_TOKEN",
        "docker.io/idconstruct/mcp-exec:v0.5.4"
      ],
      "env": {
        "MCP_EXEC_TRANSPORT": "${MCP_EXEC_TRANSPORT}",
        "MCP_EXEC_DEFAULT_TIMEOUT_S": "${MCP_EXEC_DEFAULT_TIMEOUT_S}",
        "MCP_EXEC_MAX_TIMEOUT_S": "${MCP_EXEC_MAX_TIMEOUT_S}",
        "MCP_EXEC_MAX_OUTPUT_BYTES": "${MCP_EXEC_MAX_OUTPUT_BYTES}",
        "MCP_EXEC_MAX_STDIN_BYTES": "${MCP_EXEC_MAX_STDIN_BYTES}",
        "MCP_EXEC_AUTH_TOKEN": "${MCP_EXEC_AUTH_TOKEN}"
      }
    }
  }
}
    #!/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 exec -e "MCP_EXEC_TRANSPORT=${MCP_EXEC_TRANSPORT}" -e "MCP_EXEC_DEFAULT_TIMEOUT_S=${MCP_EXEC_DEFAULT_TIMEOUT_S}" -e "MCP_EXEC_MAX_TIMEOUT_S=${MCP_EXEC_MAX_TIMEOUT_S}" -e "MCP_EXEC_MAX_OUTPUT_BYTES=${MCP_EXEC_MAX_OUTPUT_BYTES}" -e "MCP_EXEC_MAX_STDIN_BYTES=${MCP_EXEC_MAX_STDIN_BYTES}" -e "MCP_EXEC_AUTH_TOKEN=${MCP_EXEC_AUTH_TOKEN}" -- docker run -i --rm -e MCP_EXEC_TRANSPORT -e MCP_EXEC_DEFAULT_TIMEOUT_S -e MCP_EXEC_MAX_TIMEOUT_S -e MCP_EXEC_MAX_OUTPUT_BYTES -e MCP_EXEC_MAX_STDIN_BYTES -e MCP_EXEC_AUTH_TOKEN docker.io/idconstruct/mcp-exec:v0.5.4

    {
  "mcpServers": {
    "exec": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_EXEC_TRANSPORT",
        "-e",
        "MCP_EXEC_DEFAULT_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_OUTPUT_BYTES",
        "-e",
        "MCP_EXEC_MAX_STDIN_BYTES",
        "-e",
        "MCP_EXEC_AUTH_TOKEN",
        "docker.io/idconstruct/mcp-exec:v0.5.4"
      ],
      "env": {
        "MCP_EXEC_TRANSPORT": "${MCP_EXEC_TRANSPORT}",
        "MCP_EXEC_DEFAULT_TIMEOUT_S": "${MCP_EXEC_DEFAULT_TIMEOUT_S}",
        "MCP_EXEC_MAX_TIMEOUT_S": "${MCP_EXEC_MAX_TIMEOUT_S}",
        "MCP_EXEC_MAX_OUTPUT_BYTES": "${MCP_EXEC_MAX_OUTPUT_BYTES}",
        "MCP_EXEC_MAX_STDIN_BYTES": "${MCP_EXEC_MAX_STDIN_BYTES}",
        "MCP_EXEC_AUTH_TOKEN": "${MCP_EXEC_AUTH_TOKEN}"
      }
    }
  }
}
    {
  "servers": {
    "exec": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_EXEC_TRANSPORT",
        "-e",
        "MCP_EXEC_DEFAULT_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_TIMEOUT_S",
        "-e",
        "MCP_EXEC_MAX_OUTPUT_BYTES",
        "-e",
        "MCP_EXEC_MAX_STDIN_BYTES",
        "-e",
        "MCP_EXEC_AUTH_TOKEN",
        "docker.io/idconstruct/mcp-exec:v0.5.4"
      ],
      "env": {
        "MCP_EXEC_TRANSPORT": "${MCP_EXEC_TRANSPORT}",
        "MCP_EXEC_DEFAULT_TIMEOUT_S": "${MCP_EXEC_DEFAULT_TIMEOUT_S}",
        "MCP_EXEC_MAX_TIMEOUT_S": "${MCP_EXEC_MAX_TIMEOUT_S}",
        "MCP_EXEC_MAX_OUTPUT_BYTES": "${MCP_EXEC_MAX_OUTPUT_BYTES}",
        "MCP_EXEC_MAX_STDIN_BYTES": "${MCP_EXEC_MAX_STDIN_BYTES}",
        "MCP_EXEC_AUTH_TOKEN": "${MCP_EXEC_AUTH_TOKEN}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.inhuman/mcp-exec
    • 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.