This record as markdown: /tools/io-github-dave-london-docker/info.md
What info does on Docker
AI agents call info to retrieve information from Docker without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why info is rated Low
The tool name 'info' and context of Docker operations (ps, images, logs) strongly indicate this retrieves Docker metadata or container information. The incomplete description lowers confidence, but the pattern of read-only inspection tools in a Docker operations server supports Read classification. If the tool runs code or arbitrary Docker commands, severity would be higher.
From the tool's definition Tool name 'info' combined with server providing 'Structured Docker operations (ps, images, logs, build)' suggests a read-only operation. However, description is incomplete ('Runs' with no continuation).
Attacks that exploit this kind of access
The rule that runs info 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 info, this is the rule to start with:
info is read-only, so it stays allowed. 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 info call is checked against it from then on.
Questions about info
Runs. It is categorised as a Read tool in the Docker MCP Server, which means it retrieves data without modifying state.
Register the Docker MCP server in PolicyLayer and add a rule for info: 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.
info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the info 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 info. 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.
info 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.
This server
Across the catalogue