AI agents call compose-logs to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing log information from Docker Compose services. It is a read-only operation with no side effects, no code execution, and no data modification. The blast radius is minimal because logs are typically informational and retrieved logs cannot harm the system; however, logs may contain sensitive information, which prevents a 'critical' severity but does not escalate beyond 'low' since the tool…
From the tool's definition 'Retrieves Docker Compose service logs' — the tool fetches and returns log data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Retrieves Docker Compose service logs as structured entries. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for compose-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 Python. Nothing to install.
compose-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 compose-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 compose-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.
compose-logs is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
compose-logs is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →