AI agents use collect_article 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.
This tool saves/bookmarks an article to the user's collection on Juejin. It creates a new association (favorite/bookmark) which is a reversible write operation. It does not delete data, execute code, or involve financial transactions. The authorization requirement indicates it acts on behalf of a user account, raising the blast radius slightly if misused to spam collections.
From the tool's definition 收藏文章(需要授权)— 'collect article' (requires authorization); bookmarking/favoriting an article creates a new saved record
Attacks that exploit this kind of access
收藏文章(需要授权). 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.
Register the Juejin MCP server in PolicyLayer and add a rule for collect_article: 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.
collect_article is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the collect_article 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 collect_article. 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.
collect_article 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 →