Request a graceful Bernstein shutdown by writing a SHUTDOWN signal. Writes .sdd/runtime/signals/SHUTDOWN in the project directory, which the orchestrator detects and shuts down gracefully. Args: workdir: Project root directory (default: current directory). Returns: Confirmation message.
AI agents invoke bernstein_stop to trigger actions in Bernstein - Multi-agent orchestration. 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.
While the tool writes to a file (which could suggest Write category), the primary effect is triggering an external operation—graceful shutdown of a multi-agent orchestration system.
From the tool's definition Tool writes a SHUTDOWN signal file (`.sdd/runtime/signals/SHUTDOWN`) to trigger orchestrator shutdown. Description states it 'Request a graceful Bernstein shutdown' and 'the orchestrator detects and shuts down gracefully.' This is an external operation…
Risk signalsAdmin/system-level operation
Documented attack patterns abuse exactly the kind of access bernstein_stop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bernstein - Multi-agent orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for bernstein_stop:
{
"version": "1",
"default": "deny",
"tools": {
"bernstein_stop": {
"limits": [
{
"counter": "bernstein_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bernstein_stop 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.
Request a graceful Bernstein shutdown by writing a SHUTDOWN signal. Writes .sdd/runtime/signals/SHUTDOWN in the project directory, which the orchestrator detects and shuts down gracefully. Args: workdir: Project root directory (default: current directory). Returns: Confirmation message. It is categorised as a Execute tool in the Bernstein - Multi-agent orchestration MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bernstein - Multi-agent orchestration MCP server in PolicyLayer and add a rule for bernstein_stop: 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 Bernstein - Multi-agent orchestration. Nothing to install.
bernstein_stop 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 bernstein_stop 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 bernstein_stop. 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.
bernstein_stop is provided by the Bernstein - Multi-agent orchestration MCP server (sipyourdrink-ltd/bernstein). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Bernstein - Multi-agent orchestration tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 Bernstein - Multi-agent orchestration tools catalogued and risk-classified — across an index of 42,500+ MCP servers.