AI agents call search_pins 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 performs keyword search and content analysis on publicly available Juejin pins (trending topics). It is a retrieval operation with no side effects—no data is created, modified, deleted, or executed. The Chinese description confirms it is purely a search function ('搜索' = search, '分析' = analyze). Typical blast radius from misuse would be limited to information disclosure, warranting low severity.
From the tool's definition Tool name 'search_pins' and description '搜索掘金沸点，支持关键词搜索和内容分析' (search Juejin pins, supports keyword search and content analysis) indicate a search/query operation that retrieves data without modifying it.
Attacks that exploit this kind of access
搜索掘金沸点，支持关键词搜索和内容分析. 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 search_pins: 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.
search_pins 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 search_pins 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 search_pins. 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.
search_pins 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 →