Delete a credential with parameter: name (required)
AI agents call delete_credential to permanently remove resources in Databricks Permissions MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting credentials is a destructive action that cannot be undone. Loss of credentials can break authentication workflows, disable access to resources, and require manual recovery. The blast radius is high because dependent systems may lose access to services, but not universally critical (differs from financial or complete system compromise).
From the tool's definition Tool name 'delete_credential' combined with description 'Delete a credential' indicates irreversible deletion of authentication credentials. The parameter 'name (required)' specifies which credential to remove.
Attacks that exploit this kind of access
Delete a credential with parameter: name (required). It is categorised as a Destructive tool in the Databricks Permissions MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Databricks Permissions MCP Server MCP server in PolicyLayer and add a rule for delete_credential: 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 Databricks Permissions MCP Server. Nothing to install.
delete_credential 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_credential 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_credential. 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_credential is provided by the Databricks Permissions MCP Server MCP server (justtryai/databricks-permissions-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 →