update_recommendations · Juejin MCP: Risk & Policy

WHAT IT DOES

What update_recommendations does on Juejin

AI agents use update_recommendations to create or update resources in Juejin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Juejin environment.

WHY IT NEEDS A POLICY

Why update_recommendations needs a policy

This tool creates or modifies user preference data reversibly (recommendations can be updated again). It does not delete data irreversibly, execute external code, move money, or perform destructive operations. The modification is scoped to recommendation settings and user interest associations, making it a Write-category tool.

From the tool's definition Tool name 'update_recommendations' combined with description indicating it modifies user recommendations based on behavior and interests. The verb '更新' (update) in Chinese explicitly indicates modification of data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_recommendations Rate-limited

update_recommendations stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_recommendations": {
      "limits": [
        {
          "counter": "update_recommendations_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Juejin, so you can run agents against it safely.

FAQ

Questions about update_recommendations

What does the update_recommendations tool do? +

更新用户推荐，基于最新的用户行为和兴趣. It is categorised as a Write tool in the Juejin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_recommendations? +

Register the Juejin MCP server in PolicyLayer and add a rule for update_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.

What risk level is update_recommendations? +

update_recommendations is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_recommendations? +

Yes. Add a rate_limit block to the update_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.

How do I block update_recommendations completely? +

Set action: deny in the PolicyLayer policy for update_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.

What MCP server provides update_recommendations? +

update_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.