Restart a container
AI agents invoke docker_container_restart to trigger actions in Docker MCP. 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.
Restarting a container is an Execute action—it triggers external operations whose effects depend on arguments (which container to restart). While not destructive (data persists), it causes service interruption and is a significant operational action. Severity is high because an AI agent could restart critical containers, causing downtime or service disruption in production environments.
From the tool's definition Tool name 'docker_container_restart' and description 'Restart a container' indicate an action that restarts a running Docker container. This is an operational command that triggers external effects (stopping and starting container processes).
Attacks that exploit this kind of access
Restart a container. It is categorised as a Execute tool in the Docker MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docker MCP server in PolicyLayer and add a rule for docker_container_restart: 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. Nothing to install.
docker_container_restart 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 docker_container_restart 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 docker_container_restart. 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.
docker_container_restart is provided by the Docker MCP server (sondt2709/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 →