Get log output from the last N seconds.
AI agents call tail_log to retrieve information from Unreal Editor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries log data (similar to the Unix 'tail' command for reading file contents). It has no side effects—it does not create, modify, delete, or execute anything. It simply reads historical log information, making it a Read category tool with low severity since log access itself carries minimal risk when used appropriately in a development context.
From the tool's definition Tool name 'tail_log' and description 'Get log output from the last N seconds' indicate retrieval of existing log data with no modification or execution of commands.
Attacks that exploit this kind of access
Get log output from the last N seconds. It is categorised as a Read tool in the Unreal Editor MCP Server, which means it retrieves data without modifying state.
Register the Unreal Editor MCP server in PolicyLayer and add a rule for tail_log: 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 Unreal Editor. Nothing to install.
tail_log 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 tail_log 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 tail_log. 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.
tail_log is provided by the Unreal Editor MCP server (tumourlove/deprecated-unreal-editor-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 →