// SCAN REPORT

MCP Container Tools

25 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

6 can modify or destroy data

19 read-only

25 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCP Container Tools ↓

TOOL MAP

What MCP Container Tools exposes to your agents

Read (19) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Container Tools tools

Destructive · High compose_down Docker Compose 'down' command stops and removes containers, networks, and optionally volumes/images. Execute · High compose_restart This tool executes a Docker Compose command that restarts services, causing observable side effects in a live environment (downtime, state transitions). Execute · High compose_up This tool triggers the execution of containerized applications and their dependencies, which qualifies as Execute rather than Write. Execute · Critical docker_exec This tool allows running arbitrary commands inside containers, which can modify system state, access sensitive data, exfiltrate information, or compromise the container and potentially the host system.

6 of MCP Container Tools's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Container Tools

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Container Tools, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "compose_down": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "azure_availability": {
    "limits": [
      {
        "counter": "azure_availability_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Container Tools — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP CONTAINER TOOLS →

Instant setup, no code required.

FULL CATALOGUE

All 25 MCP Container Tools tools

DESTRUCTIVE 1 tools

Destructive compose_down Stop Docker Compose services

EXECUTE 5 tools

Execute azure_query Run a custom Kusto query on Application Insights logs Execute compose_restart Restart Docker Compose services Execute compose_up Start Docker Compose services Execute docker_exec Execute a command inside a running container Execute k8s_exec Execute a command in a pod

READ 19 tools

Read azure_availability Query availability test results Read azure_dependencies Query external dependencies (HTTP, SQL, etc.) Read azure_exceptions Query application exceptions and errors Read azure_metrics Query Application Insights metrics Read azure_requests Query HTTP requests to your application Read azure_traces Query application traces and logs Read compose_logs Read logs from Docker Compose services Read compose_ps List Docker Compose services and their status Read docker_inspect Get detailed information about a container Read docker_logs Read logs from a Docker container (local or remote) Read docker_ps List Docker containers (local or remote) Read k8s_contexts List available Kubernetes contexts Read k8s_deployment_logs Read logs from all pods in a deployment Read k8s_describe Get detailed information about a pod Read k8s_events Get events for a namespace or pod Read k8s_logs Read logs from a Kubernetes pod Read k8s_pods List Kubernetes pods Read list_directory List contents of a directory Read read_file Read the contents of a file

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP Container Tools

Can an AI agent delete data through the MCP Container Tools MCP server? +

Yes. The MCP Container Tools server exposes 1 destructive tools including compose_down. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the MCP Container Tools MCP server expose? +

25 tools across 2 categories: Execute, Read. 19 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on MCP Container Tools? +

Register the MCP Container Tools MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Container Tools tool call.

Deterministic rules across all 25 MCP Container Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP CONTAINER TOOLS →

Instant setup, no code required.

25 MCP Container Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from MCP Container Tools's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →