Restart a container.
AI agents invoke restart_container to trigger actions in Podman 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.
Restarting a container is an Execute action because it triggers an external operation (restart) whose effects depend on which container is targeted. While reversible (unlike Destructive actions), it causes immediate state changes and can interrupt services, making it more severe than Write.
From the tool's definition Tool description: 'Restart a container.' This directly triggers an action on a running container—stopping and restarting it. The server description emphasizes 'container lifecycle operations' and 'command execution,' confirming this is an operational action.
Attacks that exploit this kind of access
Restart a container. It is categorised as a Execute tool in the Podman MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Podman MCP Server MCP server in PolicyLayer and add a rule for restart_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 Podman MCP Server. Nothing to install.
restart_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 restart_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 restart_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.
restart_container is provided by the Podman MCP Server MCP server (kunwarmahen/podman-mcp-server). 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 →