导出指定知乎收藏夹为Markdown文件
AI agents use export_collection to create or update resources in Zhihu-Collections-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zhihu-Collections-MCP environment.
This tool creates new files (Markdown output) from existing collection data. While it generates and writes files, this is reversible—files can be deleted or regenerated. It does not delete, modify, or destroy the original collections themselves, nor does it execute arbitrary code or move money.
From the tool's definition Tool description states '导出指定知乎收藏夹为Markdown文件' (export specified Zhihu collection as Markdown file). The action involves creating/generating Markdown files with exported collection data and images.
Attacks that exploit this kind of access
导出指定知乎收藏夹为Markdown文件. It is categorised as a Write tool in the Zhihu-Collections-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zhihu-Collections- MCP server in PolicyLayer and add a rule for export_collection: 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 Zhihu-Collections-MCP. Nothing to install.
export_collection 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 export_collection 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 export_collection. 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.
export_collection is provided by the Zhihu-Collections- MCP server (jasonjarvan/zhihu-collections-mcp). 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 →