Gracefully shut down the MCP server. Stops debug session if active, then exits.
AI agents call shutdown to permanently remove resources in Openocd — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Shutting down the MCP server and stopping any active debug session is an irreversible action during its execution — the server process is terminated and the debug session is ended. This cannot be undone without manually restarting the server. The blast radius is high because it disrupts all ongoing debugging/flashing operations and makes the server unavailable to all clients.
From the tool's definition Gracefully shut down the MCP server. Stops debug session if active, then exits.
Documented attack patterns abuse exactly the kind of access shutdown gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openocd, and nothing reaches the server without passing your rules. This is the rule we recommend for shutdown:
{
"version": "1",
"default": "deny",
"hide": [
"shutdown"
]
} shutdown disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Gracefully shut down the MCP server. Stops debug session if active, then exits. It is categorised as a Destructive tool in the Openocd MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Openocd MCP server in PolicyLayer and add a rule for shutdown: 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 Openocd. Nothing to install.
shutdown is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the shutdown 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 shutdown. 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.
shutdown is provided by the Openocd MCP server (luiox/openocd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openocd, 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.
14 Openocd tools catalogued and risk-classified — across an index of 43,000+ MCP servers.