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 Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical autopilot event data. While it relates to autonomous agent orchestration, the tool itself performs only read operations—it retrieves log records without side effects. The mention of pairing with 'autopilot_enable' does not change the classification of this specific tool, which is strictly a log retrieval function.
From the tool's definition Tool description explicitly states 'Retrieve the autopilot event log' and 'Shows enable/disable events, re-engagements, completions.' These are passive retrieval operations with no modification, deletion, or execution of arbitrary code.
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 Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow 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 Claude Flow. 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 Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.