Delete an item from a Cosmos DB container
AI agents call cosmosdb_item_delete to permanently remove resources in Azure MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of database items is an irreversible operation that cannot be undone without backups. This qualifies as Destructive rather than Execute because it specifically targets data removal rather than arbitrary code execution.
From the tool's definition Tool name explicitly states 'delete' and description confirms it 'Delete an item from a Cosmos DB container'. This irreversibly removes data from a persistent database.
Attacks that exploit this kind of access
Delete an item from a Cosmos DB container. It is categorised as a Destructive tool in the Azure MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Azure MCP Server MCP server in PolicyLayer and add a rule for cosmosdb_item_delete: 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 Azure MCP Server. Nothing to install.
cosmosdb_item_delete 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 cosmosdb_item_delete 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 cosmosdb_item_delete. 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.
cosmosdb_item_delete is provided by the Azure MCP Server MCP server (mashriram/azure_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →