AI agents call get_hot_feeds to retrieve information from Weibo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available feed data from Weibo. No creation, modification, deletion, or execution of external operations occurs. The 'get_' prefix and context among read-only sibling tools confirms this is a retrieval operation.
From the tool's definition Tool name 'get_hot_feeds' and sibling tools ('get_comments', 'get_fans', 'get_feeds', 'get_followers', 'get_profile', 'get_trendings', 'search_content', 'search_topics', 'search_users') are all query/retrieval operations with no modification capability.
Documented attack patterns abuse exactly the kind of access get_hot_feeds gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Weibo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_hot_feeds:
{
"version": "1",
"default": "deny",
"tools": {
"get_hot_feeds": {}
}
} get_hot_feeds is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_hot_feeds. It is categorised as a Read tool in the Weibo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weibo MCP Server MCP server in PolicyLayer and add a rule for get_hot_feeds: 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 Weibo MCP Server. Nothing to install.
get_hot_feeds 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 get_hot_feeds 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 get_hot_feeds. 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.
get_hot_feeds is provided by the Weibo MCP Server MCP server (qinyuanpei/mcp-server-weibo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Weibo MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Weibo MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.