AI agents call yfy_search_items to retrieve information from Yifangyun without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries file/folder metadata based on search criteria. It does not create, modify, delete, or execute operations—it only reads and returns search results. The blast radius of misuse is minimal: an agent could search for sensitive files but cannot access their contents (download_url requires a separate tool) or modify them. This is a standard Read-category operation.
From the tool's definition Tool description explicitly states 'Search files/folders by keyword' with support for querying across personal space, collaboration space, and department space. The action is a search/query operation with no side effects mentioned.
Attacks that exploit this kind of access
Search files/folders by keyword. Supports personal space, collaboration space, department space via department_id, or folder scope via search_in_folder. It is categorised as a Read tool in the Yifangyun MCP Server, which means it retrieves data without modifying state.
Register the Yifangyun MCP server in PolicyLayer and add a rule for yfy_search_items: 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 Yifangyun. Nothing to install.
yfy_search_items 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 yfy_search_items 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 yfy_search_items. 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.
yfy_search_items is provided by the Yifangyun MCP server (mrhegit/yifangyun-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 →