AI agents call get_recommendations to retrieve information from Juejin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a recommendation system to return personalized content suggestions. It has no side effects on data—it neither creates, modifies, deletes, nor executes external operations. It is purely a data retrieval function, making it a Read category tool with low severity since misuse would only result in potentially irrelevant recommendations without harm to the platform or user data.
From the tool's definition Tool name is 'get_recommendations' and description states '获取个性化内容推荐' (get personalized content recommendations). The function retrieves and returns recommendation data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
获取个性化内容推荐，支持多种推荐算法和过滤条件. It is categorised as a Read tool in the Juejin MCP Server, which means it retrieves data without modifying state.
Register the Juejin MCP server in PolicyLayer and add a rule for get_recommendations: 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 Juejin. Nothing to install.
get_recommendations 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_recommendations 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_recommendations. 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_recommendations is provided by the Juejin MCP server (ztxtxwd/juejin-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 →