container_docker
Docker security: audit, CIS bench, seccomp, daemon config, image scan
This record as markdown: /tools/defense/container-docker.md
What container_docker does on Defense
AI agents use container_docker to create or update resources in Defense, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defense environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | — | Docker image to scan, e.g. 'nginx:latest' |
action | string | Yes | Docker security action |
checks | string | — | Check sections, e.g. '1,2,4' |
dry_run | boolean | — | Preview changes without executing |
settings | object | — | Daemon settings to apply |
severity | string | — | Minimum severity to report |
log_level | string | — | Minimum log level |
check_type | string | — | Docker audit check type |
daemon_action | string | — | Audit or apply daemon settings |
Parameters from the server's own tool schema.
Why container_docker is rated Medium
An AI agent can call container_docker faster than any human can review: one bad instruction and it creates or modifies resources in Defense by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (18 properties)
Attacks that exploit this kind of access
The rule that runs container_docker safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For container_docker, this is the rule to start with:
container_docker stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every container_docker call is checked against it from then on.
Questions about container_docker
Docker security: audit, CIS bench, seccomp, daemon config, image scan. It is categorised as a Write tool in the Defense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
container_docker accepts 9 parameters: image, action, checks, dry_run, settings, severity, log_level, check_type, daemon_action. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Defense MCP server in PolicyLayer and add a rule for container_docker: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.
container_docker is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the container_docker rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for container_docker. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
container_docker is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defense, and thousands of servers like it.
This server
Across the catalogue