Retrieve the autopilot event log. Shows enable/disable events, re-engagements, completions. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enable + a goal description, then let cron fi...
AI agents call autopilot_log to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays event log information for autonomous agent workflows. It is a read-only operation that queries existing log entries without modifying, deleting, or executing any operations. The primary use case described (monitoring long-horizon goals across sessions) is observational. No data is created, modified, or destroyed, and no external operations are triggered.
From the tool's definition Tool name 'autopilot_log' and description 'Retrieve the autopilot event log' explicitly indicates data retrieval with no side effects. Description specifies it 'Shows enable/disable events, re-engagements, completions' — purely querying historical log data.
Attacks that exploit this kind of access
Retrieve the autopilot event log. Shows enable/disable events, re-engagements, completions. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enable + a goal description, then let cron fires advance the work. For interactive single-task sessions, native Task is fine. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for autopilot_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 Ruflo. Nothing to install.
autopilot_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 autopilot_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 autopilot_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.
autopilot_log is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
autopilot_log is one line of Ruflo'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 →