AI agents call delete_run to permanently remove resources in TestRail MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the description is empty (lowering confidence slightly from 0.95 to 0.92), the explicit 'delete_' prefix clearly indicates this tool irreversibly removes data. Deletion of test runs cannot be undone and represents a destructive action with potential blast radius if an AI agent deletes important test execution records. This is more severe than Write operations and falls squarely into the Destructive category.
From the tool's definition Tool name is 'delete_run' which indicates irreversible deletion. Sibling tools include other destructive operations (delete_case, delete_dataset, delete_project), confirming a pattern of deletion operations on TestRail entities.
Documented attack patterns abuse exactly the kind of access delete_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TestRail MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_run:
{
"version": "1",
"default": "deny",
"hide": [
"delete_run"
]
}delete_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.
delete_run. It is categorised as a Destructive tool in the TestRail MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TestRail MCP Server MCP server in PolicyLayer and add a rule for delete_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 TestRail MCP Server. Nothing to install.
delete_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 delete_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 delete_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.
delete_run is provided by the TestRail MCP Server MCP server (sker65/testrail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TestRail 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.
29 TestRail MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.