Delete an experiment and all its runs. Moves to the 'deleted' lifecycle stage — not shown in UI or queries, but recoverable via the MLflow API.
AI agents call delete_experiment to permanently remove resources in MLflow MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly removes an experiment and all associated runs from normal access, hiding them from UI and queries. Although MLflow marks this as recoverable 'via the MLflow API', the primary action is destructive deletion of data. This constitutes an irreversible or difficult-to-reverse operation on a potentially large dataset (entire experiment with multiple runs), warranting the Destructive category.
From the tool's definition delete_experiment: Delete an experiment and all its runs. Moves to the 'deleted' lifecycle stage — not shown in UI or queries, but recoverable via the MLflow API.
Documented attack patterns abuse exactly the kind of access delete_experiment gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MLflow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_experiment:
{
"version": "1",
"default": "deny",
"hide": [
"delete_experiment"
]
}delete_experiment 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.
Delete an experiment and all its runs. Moves to the 'deleted' lifecycle stage — not shown in UI or queries, but recoverable via the MLflow API. It is categorised as a Destructive tool in the MLflow MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for delete_experiment: 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 MLflow MCP Server. Nothing to install.
delete_experiment 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 delete_experiment 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 delete_experiment. 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.
delete_experiment is provided by the MLflow MCP Server MCP server (kkruglik/mlflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MLflow 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.
40 MLflow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.