Rename a Docker container
AI agents use rename_container to create or update resources in Docker MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docker MCP Server environment.
Renaming a container is a reversible metadata modification operation (Write category). Severity is medium because while the operation itself is safe, renaming a running or important container could cause service disruption if dependent systems rely on the old name, and incorrect renaming could impact container identification and orchestration.
From the tool's definition Tool description states 'Rename a Docker container' which modifies container metadata reversibly. The name/metadata can be changed again without data loss or cascade effects.
Attacks that exploit this kind of access
Rename a Docker container. It is categorised as a Write tool in the Docker MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docker MCP Server MCP server in PolicyLayer and add a rule for rename_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.
rename_container is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rename_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 rename_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.
rename_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 →