Detailed task progress broken down by source (team-tasks, swarm-tasks, file-checklist). 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 ...
AI agents call autopilot_progress 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's core function is to fetch and report progress metrics and status—a read-only operation with no side effects. While it is part of an orchestration system and mentions pairing with autopilot_enable, the tool itself performs introspection/querying of task state rather than execution or modification. The use case (resume work across sessions, monitor long-horizon goals) is consistent with status retrieval.
From the tool's definition Tool retrieves 'detailed task progress' status information across multiple sources (team-tasks, swarm-tasks, file-checklist).
Attacks that exploit this kind of access
Detailed task progress broken down by source (team-tasks, swarm-tasks, file-checklist). 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_progress: 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_progress 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_progress 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_progress. 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_progress 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.