Read logs from a Docker container (local or remote)
AI agents call docker_logs to retrieve information from MCP Container Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic information from containers with no side effects. While logs may contain sensitive information, the read-only nature and lack of execution capability place it in the Read category. Severity is low because accessing logs alone does not directly compromise system integrity, though care should be taken regarding log content sensitivity in specific deployments.
From the tool's definition Tool name 'docker_logs' and description 'Read logs from a Docker container (local or remote)' both explicitly indicate retrieval of log data without modification or execution.
Attacks that exploit this kind of access
Read logs from a Docker container (local or remote). It is categorised as a Read tool in the MCP Container Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Container Tools MCP server in PolicyLayer and add a rule for docker_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 MCP Container Tools. Nothing to install.
docker_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 docker_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 docker_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.
docker_logs is provided by the MCP Container Tools MCP server (simseksem/mcp-container-tools). 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 →