autopilot_config
Configure autopilot limits: max iterations (1-1000), timeout in minutes (1-1440), and task sources. 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...
This record as markdown: /tools/io-github-ruvnet-claude-flow/autopilot-config.md
What autopilot_config does on Claude Flow
AI agents use autopilot_config to create or update resources in Claude Flow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
Why autopilot_config is rated Medium
This tool creates or modifies configuration settings that control autonomous agent behavior—iterations, timeouts, and task resumption. While not destructive (changes are reversible), it goes beyond read-only querying. The ability to set max iterations to 1000 and timeouts up to 1440 minutes means a misconfigured goal could cause sustained resource consumption or unintended autonomous operations.
From the tool's definition Tool enables configuration of autopilot parameters (max iterations, timeout, task sources) that modify system behavior persistently. 'Configure autopilot limits' and 'resume automatically across sessions' indicate reversible state modification.
Attacks that exploit this kind of access
The rule that runs autopilot_config safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For autopilot_config, this is the rule to start with:
autopilot_config stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every autopilot_config call is checked against it from then on.
Questions about autopilot_config
Configure autopilot limits: max iterations (1-1000), timeout in minutes (1-1440), and task sources. 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 Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for autopilot_config: 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_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the autopilot_config 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_config. 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_config 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.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue