修改 YAPI 接口
AI agents use yapi-update-interface to create or update resources in YAPI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your YAPI MCP Server environment.
This tool creates or modifies API interface data reversibly. It falls under Write category as it updates interface configurations without permanently deleting data. Severity is medium because misconfiguration of API interfaces could impact API consumers and integrations, but changes are reversible through subsequent updates.
From the tool's definition Tool name contains 'update' and description states '修改 YAPI 接口' (modify YAPI interface), indicating it modifies existing API interface documentation/definitions.
Attacks that exploit this kind of access
修改 YAPI 接口. It is categorised as a Write tool in the YAPI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the YAPI MCP Server MCP server in PolicyLayer and add a rule for yapi-update-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 YAPI MCP Server. Nothing to install.
yapi-update-interface 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 yapi-update-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-update-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-update-interface is provided by the YAPI MCP Server MCP server (w-abel-jia/yapi-interface-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 →