AI agents call yapi_search_interface to retrieve information from Mcp Yapi 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 API interface data from YApi without side effects. Searching API documentation by name or path is a read-only operation with no ability to modify, delete, or execute code. The blast radius of misuse is minimal—worst case would be retrieving unwanted API documentation details.
From the tool's definition Tool name 'yapi_search_interface' and description indicate search functionality ('搜索接口' = search interfaces). The description specifies searching by interface name and path, with no modification, deletion, or code execution capability.
Attacks that exploit this kind of access
在YApi项目中搜索接口,支持按接口名称、路径搜索. It is categorised as a Read tool in the Mcp Yapi MCP Server, which means it retrieves data without modifying state.
Register the Mcp Yapi MCP server in PolicyLayer and add a rule for yapi_search_interface: 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 Mcp Yapi. Nothing to install.
yapi_search_interface 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 yapi_search_interface 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 yapi_search_interface. 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.
yapi_search_interface is provided by the Mcp Yapi MCP server (tstonelee/mcp-yapi-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 →