run_container

Run an image in a new Docker container (preferred over create_container + start_container)

SERVERDocker SOURCE@ckreiling/mcp-server-docker

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity verified Pull the record →

This record as markdown: /tools/docker/run-container.md

WHAT IT DOES

What run_container does on Docker

AI agents invoke run_container to trigger actions in Docker. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why run_container is rated High

This tool executes code by instantiating and running a Docker container. While not inherently destructive (containers can be ephemeral), it can execute arbitrary workloads, access host resources, make network calls, or cause side effects depending on the image and runtime configuration. This makes it Execute rather than Write (not merely creating data reversibly) or Read (actively runs code).

From the tool's definition Tool description states 'Run an image in a new Docker container', which executes arbitrary containerized code/applications.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_container safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_container, this is the rule to start with:

run_container Rate-limited

run_container stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_container": {
      "limits": [
        {
          "counter": "run_container_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Docker, apply this rule, and every run_container call is checked against it from then on.

FAQ

Questions about run_container

What does the run_container tool do? +

Run an image in a new Docker container (preferred over create_container + start_container). It is categorised as a Execute tool in the Docker MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_container? +

Register the Docker MCP server in PolicyLayer and add a rule for run_container: 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 Docker. Nothing to install.

What risk level is run_container? +

run_container is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_container? +

Yes. Add a rate_limit block to the run_container 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.

How do I block run_container completely? +

Set action: deny in the PolicyLayer policy for run_container. 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.

What MCP server provides run_container? +

run_container is provided by the Docker MCP server (@ckreiling/mcp-server-docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Docker, and thousands of servers like it.

This server

All 19 Docker tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →