AI agents call xhs_get_my_profile to retrieve information from XHS-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and queries profile data about the authenticated user. It performs no creation, modification, deletion, code execution, or financial operations. The data returned is metadata about the user's account that is already accessible to the authenticated user through normal UI interaction. No blast radius from misuse.
From the tool's definition Tool name 'xhs_get_my_profile' and description '获取当前登录用户的资料信息（包括账户名、粉丝数、关注数、获赞与收藏等）' [retrieves current logged-in user profile information including account name, follower count, following count, likes and favorites, etc.] indicate data retrieval with no…
Attacks that exploit this kind of access
获取当前登录用户的资料信息（包括账户名、粉丝数、关注数、获赞与收藏等）. It is categorised as a Read tool in the XHS-MCP MCP Server, which means it retrieves data without modifying state.
Register the XHS- MCP server in PolicyLayer and add a rule for xhs_get_my_profile: 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 XHS-MCP. Nothing to install.
xhs_get_my_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the xhs_get_my_profile 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 xhs_get_my_profile. 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.
xhs_get_my_profile is provided by the XHS- MCP server (lastkimi/xhs-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 →