start_auto_cycle
AI agents invoke start_auto_cycle to trigger actions in Tmux MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers automated execution of tmux workflows (exit/continue cycles) whose effects depend on the tmux session state and configured automation rules. It is not merely reading data (no Read), not reversibly modifying data (no Write), and not destructive by itself (no Destructive). It executes external operations through tmux process control, making it Execute.
From the tool's definition The tool name 'start_auto_cycle' combined with server description mentioning 'automated workflow features like exit/continue cycles' indicates execution of automated tmux operations.
Attacks that exploit this kind of access
start_auto_cycle. It is categorised as a Execute tool in the Tmux MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tmux MCP Server MCP server in PolicyLayer and add a rule for start_auto_cycle: 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 Tmux MCP Server. Nothing to install.
start_auto_cycle is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_auto_cycle 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 start_auto_cycle. 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.
start_auto_cycle is provided by the Tmux MCP Server MCP server (rinadelph/tmux-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →