AI agents call terminate_run to permanently remove resources in Mcp Dagster — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Terminating an in-progress run is an irreversible action: any partial work may be lost, downstream dependencies may be skipped, and the run cannot be restarted from where it left off. This matches the Destructive category. The blast radius is high because prematurely killing a pipeline run can corrupt data state, break dependent jobs, and require manual remediation.
From the tool's definition 'Terminate an in-progress Dagster run' — terminating a running pipeline is irreversible; the run cannot be resumed once stopped.
Documented attack patterns abuse exactly the kind of access terminate_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Dagster, and nothing reaches the server without passing your rules. This is the rule we recommend for terminate_run:
{
"version": "1",
"default": "deny",
"hide": [
"terminate_run"
]
}terminate_run 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.
Terminate an in-progress Dagster run. It is categorised as a Destructive tool in the Mcp Dagster MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Dagster MCP server in PolicyLayer and add a rule for terminate_run: 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 Mcp Dagster. Nothing to install.
terminate_run 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 terminate_run 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 terminate_run. 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.
terminate_run is provided by the Mcp Dagster MCP server (kyryl-opens-ml/mcp-server-dagster). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Dagster, 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.
9 Mcp Dagster tools catalogued and risk-classified — across an index of 43,000+ MCP servers.