Clear stored credentials from session
AI agents call clear_credentials to permanently remove resources in Yandex Cloud MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing stored credentials is an irreversible destructive action within the session context: once credentials are removed, they cannot be recovered from the session. This is not a simple read or write but a permanent deletion of authentication state. Misuse by an AI agent could lock out access to Yandex Cloud resources until credentials are re-entered.
From the tool's definition clear_credentials — 'Clear stored credentials from session'
Attacks that exploit this kind of access
Clear stored credentials from session. It is categorised as a Destructive tool in the Yandex Cloud MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Yandex Cloud MCP Server MCP server in PolicyLayer and add a rule for clear_credentials: 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 Yandex Cloud MCP Server. Nothing to install.
clear_credentials 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 clear_credentials 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 clear_credentials. 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.
clear_credentials is provided by the Yandex Cloud MCP Server MCP server (romati88/ycmcp). 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 →