This record as markdown: /tools/io-github-dave-london-docker/get.md
What get does on Docker
AI agents invoke get 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 get is rated High
This tool performs 'go get' equivalent operations: it downloads remote packages AND installs them into the environment. The installation step constitutes execution of external code/build steps and modifies the system state. While partially a Write operation, the execution of build/install processes and the ability to pull arbitrary remote code elevates this to Execute.
From the tool's definition 'Downloads and installs Go packages and their dependencies' — installs software onto the system
Attacks that exploit this kind of access
The rule that runs get 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 get, this is the rule to start with:
get 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 get call is checked against it from then on.
Questions about get
Downloads and installs Go packages and their dependencies. 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 get: 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.
get 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 get 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 get. 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.
get is provided by the Docker MCP server (@paretools/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