AI agents invoke restart to trigger actions in tmux-claude 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.
Restarting instances is an Execute category action because it runs/triggers an external operation (tmux instance restart) rather than merely reading or writing data. While not destructive, it alters system state and could disrupt running workloads if misused by an agent. The '--continue flag' suggests parameterization that could affect restart behavior.
From the tool's definition Tool performs 'Restart a dead instance' — a command that triggers external operations (process restart) whose effects depend on the instance state and arguments ('--continue flag'). This is an operational action that executes system-level orchestration.
Documented attack patterns abuse exactly the kind of access restart gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and tmux-claude MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for restart:
{
"version": "1",
"default": "deny",
"tools": {
"restart": {
"limits": [
{
"counter": "restart_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}restart stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Restart a dead instance using --continue flag. It is categorised as a Execute tool in the tmux-claude MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the tmux-claude MCP Server MCP server in PolicyLayer and add a rule for restart: 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-claude MCP Server. Nothing to install.
restart 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 restart 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 restart. 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.
restart is provided by the tmux-claude MCP Server MCP server (michael-abdo/tmux-claude-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from tmux-claude MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 tmux-claude MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.