This record as markdown: /tools/docker/pull-image.md
What pull_image does on Docker
AI agents invoke pull_image to trigger actions in Docker. 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.
Why pull_image is rated High
Pulling a Docker image triggers an external network operation that fetches and stores image data from a remote registry onto the local system. It is not a simple read (it has side effects: downloading and storing image layers locally), not a write to user data, and not destructive.
From the tool's definition Tool name: 'pull_image', description: 'Pull a Docker image'
Attacks that exploit this kind of access
The rule that runs pull_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 pull_image, this is the rule to start with:
pull_image stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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 pull_image call is checked against it from then on.
Questions about pull_image
Pull a Docker image. It is categorised as a Execute tool in the Docker 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 pull_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.
pull_image 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 pull_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 pull_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.
pull_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.
Across the catalogue