Create a new Docker container
AI agents invoke create_container to trigger actions in Docker 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.
Creating a Docker container involves spawning a new execution environment that can run arbitrary code, mount host volumes, expose network ports, and consume system resources. While not purely destructive, the blast radius is high because a misconfigured or malicious container can compromise host security, exhaust resources, or serve as a pivot point for further attacks.
From the tool's definition 'Create a new Docker container' - spawns a new containerized process environment on the host system
Attacks that exploit this kind of access
Create a new Docker container. It is categorised as a Execute tool in the Docker MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docker MCP Server MCP server in PolicyLayer and add a rule for create_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 MCP Server. Nothing to install.
create_container is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_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.
Set action: deny in the PolicyLayer policy for create_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.
create_container is provided by the Docker MCP Server MCP server (swartdraak/docker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →