docker_run

Run a Docker container

SERVERCode MCP Server SOURCEagentics-ai/code-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/agentics-ai-code-mcp/docker-run.md

WHAT IT DOES

What docker_run does on Code MCP Server

AI agents invoke docker_run to trigger actions in Code MCP Server. 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 docker_run is rated High

Running Docker containers is a form of code/command execution that can have wide-ranging side effects including network access, filesystem modifications, and resource consumption. The blast radius is critical because container runtime arguments could expose host systems, execute malicious payloads, or compromise security boundaries.

From the tool's definition Tool name 'docker_run' combined with description 'Run a Docker container' indicates execution of arbitrary containerized code. Docker containers can access host resources, network, and filesystems depending on runtime flags.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs docker_run safely

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

docker_run Rate-limited

docker_run 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": {
    "docker_run": {
      "limits": [
        {
          "counter": "docker_run_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 Code MCP Server, apply this rule, and every docker_run call is checked against it from then on.

FAQ

Questions about docker_run

What does the docker_run tool do? +

Run a Docker container. It is categorised as a Execute tool in the Code MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on docker_run? +

Register the Code MCP Server MCP server in PolicyLayer and add a rule for docker_run: 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 Code MCP Server. Nothing to install.

What risk level is docker_run? +

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

Can I rate-limit docker_run? +

Yes. Add a rate_limit block to the docker_run 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 docker_run completely? +

Set action: deny in the PolicyLayer policy for docker_run. 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 docker_run? +

docker_run is provided by the Code MCP Server MCP server (agentics-ai/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Code MCP Server, and thousands of servers like it.

This server

All 73 Code MCP Server 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 →