AI agents call get-logs to retrieve information from Docker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves container logs, which is a data retrieval operation with no side effects. It does not create, modify, delete, or execute code—it only reads and returns information about container state. The blast radius of misuse is minimal; an attacker could gain visibility into application behavior but cannot directly harm systems or data.
From the tool's definition Tool name 'get-logs' and description 'Retrieve the latest logs for a specified Docker container' indicate a read-only operation that queries existing log data without modifying, deleting, or executing any operations.
Attacks that exploit this kind of access
Retrieve the latest logs for a specified Docker container. 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 get-logs: 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-logs 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 get-logs 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-logs. 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-logs is provided by the Docker MCP server (quantgeekdev/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 →