This record as markdown: /tools/docker/push-image.md
What push_image does on Docker
AI agents use push_image to create or update resources in Docker, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docker environment.
Why push_image is rated Medium
Pushing an image to a registry is a write operation that creates or uploads data to a remote system. It is reversible (images can be deleted or overwritten in registries), so it is not Destructive. It does not execute arbitrary code on the host system and does not move money, making it Write rather than Execute or Financial.
From the tool's definition Tool named 'push_image' with description 'Push a Docker image' — the action uploads/writes a Docker image to a registry, modifying state in the remote registry.
Attacks that exploit this kind of access
The rule that runs push_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For push_image, this is the rule to start with:
push_image stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Docker, apply this rule, and every push_image call is checked against it from then on.
Questions about push_image
Push a Docker image. It is categorised as a Write tool in the Docker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docker MCP server in PolicyLayer and add a rule for push_image: 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. Nothing to install.
push_image 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 push_image 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 push_image. 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.
push_image is provided by the Docker MCP server (@ckreiling/mcp-server-docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docker, and thousands of servers like it.
This server
Across the catalogue