AI agents call infra_logs_tool to retrieve information from Infra without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Log tailing is a read-only operation that queries existing log data from a running service. Even with grep filtering, it only retrieves and displays data without modifying any state. Severity is low since the worst case is exposure of sensitive data in logs, but no infrastructure changes can result from this tool.
From the tool's definition 'Tail logs from one compose service' — this retrieves log output with optional filtering via `grep` and time range via `since`. No mutation, execution, or deletion implied.
Attacks that exploit this kind of access
Tail logs from one compose service. since accepts 10m / 1h / 2d. grep is plain text. It is categorised as a Read tool in the Infra MCP Server, which means it retrieves data without modifying state.
Register the Infra MCP server in PolicyLayer and add a rule for infra_logs_tool: 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 Infra. Nothing to install.
infra_logs_tool 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 infra_logs_tool 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 infra_logs_tool. 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.
infra_logs_tool is provided by the Infra MCP server (odanree/infra-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 →