退出登录,清理掉本地的cookie信息。
AI agents use logout to create or update resources in zhihu MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your zhihu MCP Server environment.
Logout clears authentication cookies, which is a session state modification. This is reversible (user can log back in) and has no destructive or persistent side effects. It does not read data, execute external code, or move financial resources. The severity is low because the impact is limited to the current session and affects only the authenticated state of the user performing the action.
From the tool's definition Tool description: '退出登录,清理掉本地的cookie信息' (logout, clear local cookie information). The logout action modifies the local session state by clearing cookies, which is a reversible data modification operation.
Attacks that exploit this kind of access
退出登录,清理掉本地的cookie信息。. It is categorised as a Write tool in the zhihu MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the zhihu MCP Server MCP server in PolicyLayer and add a rule for 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 zhihu MCP Server. Nothing to install.
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 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 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.
logout is provided by the zhihu MCP Server MCP server (morrain/zhihumcpserver). 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 →