AI agents use tap_logout to create or update resources in Tds — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tds environment.
Logout/clearing authorization is a Write operation: it modifies authentication state reversibly. The user can log back in. This is not Destructive (no irreversible deletion), not Execute (no arbitrary command execution), and not Financial. Severity is low because the blast radius is confined to the current session—an agent logging out affects only the active session, not data integrity or broader systems.
From the tool's definition Tool description states it 'reset the user info, clear the authorization info' — operations that modify authentication state but do not delete data irreversibly nor execute arbitrary code.
Attacks that exploit this kind of access
user wants to logout from TapTap platform or reset the user info, clear the authrization info. It is categorised as a Write tool in the Tds MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tds MCP server in PolicyLayer and add a rule for tap_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 Tds. Nothing to install.
tap_logout is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the tap_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 tap_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.
tap_logout is provided by the Tds MCP server (@taptap/tds-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 →