Log out from Tulidu Sport and remove local credentials.
AI agents call tulidu_logout to permanently remove resources in Tulidu Sport — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Logging out and removing local credentials is an irreversible action in context: the stored credentials are deleted and the session is terminated. Restoring access requires re-authentication. This is more than a Write (it destroys state) and fits Destructive since the credential removal cannot be undone automatically.
From the tool's definition 'Log out from Tulidu Sport and remove local credentials' — permanently removes local credentials
Attacks that exploit this kind of access
Log out from Tulidu Sport and remove local credentials. It is categorised as a Destructive tool in the Tulidu Sport MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tulidu Sport MCP server in PolicyLayer and add a rule for tulidu_logout: 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 Tulidu Sport. Nothing to install.
tulidu_logout 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 tulidu_logout 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 tulidu_logout. 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.
tulidu_logout is provided by the Tulidu Sport MCP server (tulidu-sport/tulidu-sport-mcp). 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 →