Search past completion episodes by keyword. Requires AgentDB. 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 inte...
AI agents call autopilot_history 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 retrieves historical data about past completion episodes. It is a search/query function that does not create, modify, delete, or execute anything. While it supports autonomous agent workflows, the tool itself is purely informational. The low severity reflects minimal blast radius — misuse would only return unwanted historical records, not cause operational harm.
From the tool's definition Tool performs 'Search past completion episodes by keyword' — a query operation with no side effects. The description explicitly frames this as retrieval functionality paired with other tools (autopilot_enable, cron) that would handle state changes.
Attacks that exploit this kind of access
Search past completion episodes by keyword. Requires AgentDB. 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_history: 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_history 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_history 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_history. 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_history 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.