AI agents call delete_ontology to permanently remove resources in Fabric Ontology MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes entire ontology objects, which are foundational metadata structures in Microsoft Fabric. The deletion is permanent and will break any dependent relationships, entity types, and data bindings. This is a core destructive operation that cannot be reversed through normal means, making it Destructive rather than merely Write.
From the tool's definition Tool name 'delete_ontology' and description 'Delete an ontology' directly indicate irreversible deletion of data structures. Confirmed by server description stating 'full CRUD control of Ontology items' where 'D' = Delete.
Documented attack patterns abuse exactly the kind of access delete_ontology gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fabric Ontology MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_ontology:
{
"version": "1",
"default": "deny",
"hide": [
"delete_ontology"
]
} delete_ontology 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 ontology. It is categorised as a Destructive tool in the Fabric Ontology MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Fabric Ontology MCP Server MCP server in PolicyLayer and add a rule for delete_ontology: 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 Fabric Ontology MCP Server. Nothing to install.
delete_ontology 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_ontology 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_ontology. 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_ontology is provided by the Fabric Ontology MCP Server MCP server (tmdaidevs/ontology-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fabric Ontology 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.
45 Fabric Ontology MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.